© 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. 70528
    Prev
    Next
    INDEX
    Explanations

    have a, good to, She looks

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

    legal, technical, and foreign terms

    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
     {
    0.46
    一位
    0.40
    sp
    0.40
    迭
    0.40
    soe
    0.40
     ہمس
    0.39
     杯
    0.39
     Vì
    0.38
    time
    0.38
     มัน
    0.38
    POSITIVE LOGITS
     vreau
    0.53
     prosecution
    0.46
    കേന്ദ്രം
    0.46
    Prosec
    0.46
     السماء
    0.45
    탄소년단
    0.44
    Defendant
    0.44
     autonomy
    0.44
     yarı
    0.44
     traversal
    0.44
    Activations Density 0.001%

    No Known Activations