© 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. 67386
    Prev
    Next
    INDEX
    Explanations

    grandmother Mary, confidence, Jill De, tell us

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

    parentheses or specific structures

    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
    вий
    0.47
    ４
    0.45
    句話
    0.44
    KEN
    0.43
    ้ำ
    0.43
    َہ
    0.43
    Replies
    0.41
     Бушлай
    0.41
     بلغ
    0.41
    There
    0.40
    POSITIVE LOGITS
     (
    0.46
     VIII
    0.44
     P
    0.43
     '=',
    0.43
     XI
    0.43
     Workforce
    0.43
     USDA
    0.42
     E
    0.42
     Part
    0.42
     PD
    0.41
    Activations Density 0.000%

    No Known Activations