© 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. 817
    Prev
    Next
    INDEX
    Explanations

    car restoration and repairs

    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
     gagner
    -0.84
    amom
    -0.80
    bhp
    -0.78
    bord
    -0.77
    blockchain
    -0.74
     Wikimedijinoj
    -0.73
    urgent
    -0.71
    ッキー
    -0.71
     ベクトル
    -0.71
    chesse
    -0.70
    POSITIVE LOGITS
     Resto
    1.02
     restore
    1.01
     Nova
    1.00
     Muscle
    0.98
     Classic
    0.94
     Camaro
    0.94
     restored
    0.93
     Vintage
    0.91
     restores
    0.91
     nova
    0.90
    Activations Density 0.023%

    No Known Activations