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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1653
    Prev
    Next
    INDEX
    Explanations

    of other languages

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

    The neuron fires on prominent content words—especially multi-syllabic nouns, proper names, titles of organizations or events, and other formal, information-rich terms.

    oai_token-act-pair · o4-miniTriggered 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
    s
    0.79
    可以选择
    0.66
    可以
    0.65
    ሰ
    0.64
    ول
    0.63
    ﻁ
    0.63
    จะ
    0.62
     handcuffs
    0.61
    ﺭ
    0.61
    sau
    0.60
    POSITIVE LOGITS
     ofthe
    1.33
     of
    1.20
     của
    1.19
    ofthe
    1.04
     systému
    0.97
     econôm
    0.96
     của
    0.92
    sof
    0.89
     של
    0.88
     denna
    0.86
    Activations Density 17.571%

    No Known Activations