© 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. 132763
    Prev
    Next
    INDEX
    Explanations

    weekend or night appointments

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

    habanero, cayenne pepper, carolina reaper

    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
     =
    0.57
    0.56
    ”
    0.56
    WM
    0.55
     of
    0.55
     must
    0.55
    ↵↵
    0.54
     (
    0.53
     can
    0.53
     has
    0.53
    POSITIVE LOGITS
     홈페이지
    0.60
    .}\
    0.59
     વેબસ
    0.55
     드라마
    0.54
    ovaniyu
    0.54
    东南
    0.54
    pieceSelection
    0.52
    စျေး
    0.51
     スカート
    0.51
     заявление
    0.50
    Activations Density 0.000%

    No Known Activations