© 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. 1457
    Prev
    Next
    INDEX
    Explanations

    Okay,

    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
     (
    0.50
    Indirect
    0.47
    Contents
    0.46
    Init
    0.44
     того
    0.44
    Initialize
    0.44
    Corresponding
    0.43
    Архи
    0.43
    <h2>
    0.43
    Description
    0.42
    POSITIVE LOGITS
    ：
    0.80
     let
    0.70
    :
    0.69
     lets
    0.68
     Lets
    0.64
    ፡
    0.63
     якщо
    0.61
    】：
    0.61
     jeżeli
    0.58
     LU
    0.55
    Activations Density 0.205%

    No Known Activations