© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8375
    Prev
    Next
    INDEX
    Explanations

    documentation comments and annotations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Unless
    0.61
    ⃙
    0.57
    除非
    0.57
    盉
    0.57
    MathOperator
    0.55
    unless
    0.53
    udir
    0.53
     unless
    0.52
    directed
    0.52
    Ꮕ
    0.52
    POSITIVE LOGITS
     var
    0.64
     grid
    0.60
     bekom
    0.58
     infrastructure
    0.58
     suite
    0.57
    運輸
    0.55
     int
    0.55
     vari
    0.53
    var
    0.53
    内
    0.53
    Activations Density 0.035%

    No Known Activations