© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92006
    Prev
    Next
    INDEX
    Explanations

    at org

    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_34/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
    吊
    -0.97
    ();
    -0.97
     你
    -0.90
     puedes
    -0.90
    GraphicsUnit
    -0.87
     Nisan
    -0.85
    你可以
    -0.84
    WireFormatLite
    -0.84
     Her
    -0.83
    (!__
    -0.83
    POSITIVE LOGITS
     內
    1.00
    تهى
    0.95
     doenças
    0.89
     执行
    0.87
    étr
    0.87
    extrémité
    0.86
     bazı
    0.86
     executar
    0.86
     Tite
    0.85
    ߘ
    0.83
    Activations Density 0.043%

    No Known Activations