© 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. 99396
    Prev
    Next
    INDEX
    Explanations

    academic and code snippets

    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
    子は
    -0.79
    襖
    -0.79
    有一天
    -0.79
    岁的
    -0.78
    ững
    -0.76
     bleus
    -0.76
     amerik
    -0.75
     açúcar
    -0.75
    リビング
    -0.73
     parachoque
    -0.73
    POSITIVE LOGITS
    Ql
    0.83
    ລ
    0.81
     nhập
    0.77
    chanan
    0.74
    YZ
    0.74
    iany
    0.73
     fry
    0.73
    諷
    0.73
     Blazers
    0.72
     следу
    0.71
    Activations Density 0.010%

    No Known Activations