© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7989
    Prev
    Next
    INDEX
    Explanations

    acknowledging shortcomings

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags verbs that introduce a personal insight or revelation (e.g. “shows you that,” “you realize that,” “starting to realize that”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the word "that" when it appears in clauses introducing realizations, discoveries, or significant insights.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    statements of realization or discovery—cognitive expressions that signal someone coming to understand or learn something, often with a following “that” clause and direct address to “you.”

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متاب
    0.76
    in
    0.74
     withstand
    0.74
     endeavors
    0.74
    凭借
    0.74
     always
    0.73
     sempre
    0.73
    ir
    0.73
     whenever
    0.73
     ĝi
    0.72
    POSITIVE LOGITS
     PROBLEMS
    1.03
     مشکلات
    0.99
     समस्याएं
    0.99
     problemas
    0.96
     problèmes
    0.95
     Problems
    0.93
     problemi
    0.93
     proble
    0.91
     malnutrition
    0.91
     problems
    0.91
    Activations Density 1.294%

    No Known Activations