© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15692
    Prev
    Next
    INDEX
    Explanations

    checking conditions

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

    The neuron detects numeric literals (numbers) in code or query contexts.

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

    conditional statements or comparisons in code or technical instructions.

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

    code and query logic syntax, especially conditional/control-flow constructs, comparison operators, and SQL-style keywords and punctuation

    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_31_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
    (!
    0.95
     (!
    0.80
    Get
    0.70
    切
    0.65
    Group
    0.64
    Util
    0.64
    Try
    0.64
    Utils
    0.63
    [!
    0.63
    !
    0.63
    POSITIVE LOGITS
     bituminous
    0.69
     poumon
    0.68
     혈
    0.66
     सिव
    0.65
     sangue
    0.64
     krv
    0.64
     temperatura
    0.64
     climatic
    0.63
     кров
    0.63
     WWII
    0.63
    Activations Density 0.000%

    No Known Activations