© 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. 45325
    Prev
    Next
    INDEX
    Explanations

    capture impacts found strips descriptive presentations

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

    pulsing with light

    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
     mede
    0.45
    وتا
    0.44
     پو
    0.43
    واد
    0.41
    (),
    0.41
    avar
    0.40
    కు
    0.40
    %,
    0.40
     koko
    0.39
    ਲੀ
    0.39
    POSITIVE LOGITS
     Emission
    0.48
     épouse
    0.47
     À
    0.47
     IERC
    0.46
     মৃত্য
    0.45
    formes
    0.45
     acide
    0.45
    ショッピング
    0.44
     UVB
    0.44
     stronie
    0.43
    Activations Density 0.000%

    No Known Activations