© 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. 116155
    Prev
    Next
    INDEX
    Explanations

    javascript build tools

    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
     Giải
    -0.77
     Bạn
    -0.77
    けれど
    -0.75
    čný
    -0.70
     moth
    -0.69
     Sự
    -0.69
     akhirnya
    -0.69
    ctable
    -0.69
    ッカ
    -0.68
    Ɠ
    -0.68
    POSITIVE LOGITS
     заменить
    0.82
     compress
    0.79
     concat
    0.78
     Bower
    0.77
     rev
    0.77
    戳
    0.76
     rename
    0.76
     pulito
    0.75
    压缩
    0.74
     изменить
    0.73
    Activations Density 0.017%

    No Known Activations