© 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. 73466
    Prev
    Next
    INDEX
    Explanations

    free of charge or without modifiers

    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
     Hou
    -0.76
    нос
    -0.74
    냈
    -0.74
    Digitized
    -0.73
    راق
    -0.73
    ற்று
    -0.73
    例文帳に追加
    -0.72
     princip
    -0.71
    žová
    -0.70
     biến
    -0.69
    POSITIVE LOGITS
    ACM
    0.96
    irem
    0.79
     inexorable
    0.79
    ENIX
    0.78
     './../
    0.77
     държа
    0.76
    年度
    0.75
    匾
    0.75
    તિ
    0.75
     $
    0.75
    Activations Density 0.057%

    No Known Activations