© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98838
    Prev
    Next
    INDEX
    Explanations

    as published by

    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
    モンド
    -0.72
     Ranch
    -0.72
    мулятор
    -0.71
    relógio
    -0.71
     Vend
    -0.69
    監視
    -0.68
     Surface
    -0.68
     Herz
    -0.68
    mede
    -0.67
    cted
    -0.67
    POSITIVE LOGITS
    يست
    0.70
    тинки
    0.70
    埼玉
    0.68
    EFE
    0.68
    <0x8A>
    0.68
     eq
    0.66
     путь
    0.65
    栄
    0.64
    ազմ
    0.63
    Edit
    0.62
    Activations Density 0.043%

    No Known Activations