© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 169631
    Prev
    Next
    INDEX
    Explanations

    found and discovered

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

    unless the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     comparing
    0.60
    ール
    0.59
    輿
    0.54
     insane
    0.49
     achter
    0.48
     використа
    0.48
     immor
    0.48
     comparison
    0.47
    時間
    0.47
     overcast
    0.47
    POSITIVE LOGITS
    \}$.
    0.55
    )$;
    0.52
     کوډ
    0.50
    !);
    0.49
    )';
    0.46
    ){
    0.46
    UserInput
    0.46
    XPath
    0.45
    okan
    0.45
    Default
    0.44
    Activations Density 0.000%

    No Known Activations