© 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. 10-GEMMASCOPE-RES-131K
    7. 66834
    Prev
    Next
    INDEX
    Explanations

    code initialization and methods

    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_10/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
     семи
    -2.23
     «
    -2.11
    B
    -2.08
     he
    -1.98
    ⚌
    -1.97
     So
    -1.96
     of
    -1.95
    そして
    -1.94
     («
    -1.93
    ющие
    -1.88
    POSITIVE LOGITS
    They
    2.23
    ﮨ
    2.22
    Sebagai
    2.19
    읊
    2.19
    鲥
    2.19
    选择
    2.16
    糁
    2.13
    .’’
    2.09
    .");
    2.06
    鿬
    2.02
    Activations Density 0.001%

    No Known Activations