© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66090
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     but
    -0.94
    without
    -0.88
    RTLI
    -0.87
     JULY
    -0.85
     isang
    -0.78
    ческом
    -0.78
    glfw
    -0.78
    lho
    -0.78
    լ
    -0.77
     ilman
    -0.77
    POSITIVE LOGITS
    完结
    1.17
     その他
    0.88
    だいたい
    0.82
     Parigi
    0.82
     noon
    0.80
     ſtand
    0.79
     alcoh
    0.79
     lúc
    0.77
    ]<<"
    0.77
    Additions
    0.76
    Activations Density 0.061%

    No Known Activations