© 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. 132389
    Prev
    Next
    INDEX
    Explanations

    rules, responsibilities, and entities

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

    general idea, shrinks repeatedly, human dignity, spectrum of

    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
    پ
    0.54
    md
    0.52
    qli
    0.52
    he
    0.52
    heart
    0.51
    msk
    0.51
    ب
    0.50
    ejs
    0.50
    That
    0.49
    mc
    0.49
    POSITIVE LOGITS
    ედერ
    0.54
     상
    0.51
     minimization
    0.50
     כל
    0.49
     ਪ੍ਰ
    0.48
     mistress
    0.48
     polymorphism
    0.47
     யோ
    0.47
     הא
    0.47
     다음과
    0.46
    Activations Density 0.000%

    No Known Activations