© 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. 130617
    Prev
    Next
    INDEX
    Explanations

    facing foreclosure

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

    parameters, logging, and sensitive data

    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
    𝟮
    0.51
    ClCompile
    0.50
    važ
    0.45
     చెప్పారు
    0.45
     অ্যাক
    0.43
     政府
    0.43
    ExpressCheckout
    0.43
     আপডেট
    0.43
    <unused305>
    0.43
     主要
    0.43
    POSITIVE LOGITS
     reprend
    0.48
     nes
    0.46
     a
    0.45
     pets
    0.44
    观点
    0.44
     simbol
    0.43
     jeruk
    0.43
     Moc
    0.43
    熟悉的
    0.43
     nep
    0.43
    Activations Density 0.000%

    No Known Activations