© 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. 239307
    Prev
    Next
    INDEX
    Explanations

    course of, available from, pulled pork, discovered it

    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
     침
    0.49
     heml
    0.48
     carbohyd
    0.45
     ▪
    0.44
     不要
    0.44
    เซล
    0.44
     anatomical
    0.43
     화학
    0.43
    舧
    0.42
    gers
    0.42
    POSITIVE LOGITS
    СТИ
    0.54
    it
    0.53
    ibus
    0.50
    倬
    0.48
    queda
    0.48
     Цент
    0.47
     изд
    0.46
    existent
    0.46
    h
    0.46
    حق
    0.45
    Activations Density 0.000%

    No Known Activations