© 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. 98474
    Prev
    Next
    INDEX
    Explanations

    Google Assistant

    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
    ydney
    -0.81
    يكية
    -0.77
     paypal
    -0.75
    Sonic
    -0.74
     solange
    -0.74
    Price
    -0.71
     ferric
    -0.71
    ◟
    -0.70
    !!!!!
    -0.70
     blames
    -0.70
    POSITIVE LOGITS
     مراجعه
    0.86
    ñera
    0.85
    mpo
    0.81
     Atkinson
    0.80
    hopper
    0.77
    ﷺ
    0.77
    Vegetarian
    0.76
     Gaspar
    0.75
    Дизайн
    0.75
    QY
    0.74
    Activations Density 0.015%

    No Known Activations