© 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. 142903
    Prev
    Next
    INDEX
    Explanations

    wireless networks, cash prizes, harm legitimate

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

    dental pulp, improving turbine, heat

    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
    冚
    0.54
    𝐰
    0.50
    дко
    0.50
    ರೆ
    0.48
    эле
    0.48
    రించే
    0.47
    то
    0.46
    acterísticas
    0.46
    дым
    0.46
    assuming
    0.46
    POSITIVE LOGITS
     SI
    0.48
     GET
    0.48
     GIL
    0.48
     Kirchhoff
    0.48
     PI
    0.48
    `),
    0.47
     Bethesda
    0.47
     by
    0.47
     LL
    0.46
     Poincaré
    0.45
    Activations Density 0.000%

    No Known Activations