© 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. 59196
    Prev
    Next
    INDEX
    Explanations

    as a

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

    not equipped

    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
    rewrite
    0.45
    こちらも
    0.45
    resolvers
    0.44
    id
    0.44
    ris
    0.43
    rong
    0.42
    s
    0.42
    ok
    0.42
    い
    0.42
    helper
    0.41
    POSITIVE LOGITS
     насто
    0.48
     좋다
    0.44
     sailboats
    0.43
     tradeoffs
    0.43
     comporte
    0.43
     &/
    0.42
    вае
    0.41
     ഇഷ്ട
    0.41
     मुद्राओं
    0.41
     schafft
    0.40
    Activations Density 0.000%

    No Known Activations