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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110597
    Prev
    Next
    INDEX
    Explanations

    phone numbers and addresses

    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
     producciones
    -0.82
    鸡
    -0.77
     режи
    -0.73
    mű
    -0.72
     dropdown
    -0.72
    tım
    -0.72
     javax
    -0.71
     Nutrient
    -0.71
     증
    -0.70
    rüstung
    -0.69
    POSITIVE LOGITS
     havet
    0.88
     جای
    0.87
     Lafayette
    0.84
     gratis
    0.84
    faith
    0.83
     Faith
    0.81
    calaureate
    0.81
     palate
    0.81
     vare
    0.79
     хвати
    0.79
    Activations Density 0.100%

    No Known Activations