© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73133
    Prev
    Next
    INDEX
    Explanations

    patent numbers and codes

    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
     consente
    -1.09
    ようです
    -1.06
     frete
    -1.05
    おわりに
    -1.01
     هذا
    -1.00
     pesso
    -1.00
    /*++
    -1.00
    為に
    -0.99
    RTLE
    -0.99
     hvilket
    -0.99
    POSITIVE LOGITS
     by
    1.19
    方針
    0.94
    チャンス
    0.93
    ebly
    0.93
     in
    0.92
    情報は
    0.88
    問題は
    0.87
    orous
    0.85
    権利
    0.85
    ări
    0.85
    Activations Density 0.017%

    No Known Activations