© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34078
    Prev
    Next
    INDEX
    Explanations

    section headers and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GRATU
    -1.05
     espagnol
    -1.01
     ilmiah
    -1.00
    运转
    -0.97
     Septembre
    -0.97
    ilité
    -0.96
     Dispon
    -0.96
     vicepresidente
    -0.96
    onyms
    -0.95
    噼
    -0.95
    POSITIVE LOGITS
     if
    1.02
     antigas
    1.01
     primeiras
    1.00
     where
    0.97
     qualquer
    0.96
     at
    0.94
    losseum
    0.92
    榜
    0.92
     faça
    0.92
     obligado
    0.91
    Activations Density 0.000%

    No Known Activations