© 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. 98063
    Prev
    Next
    INDEX
    Explanations

    legal disclaimer terms

    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
    timedia
    -0.78
     betwixt
    -0.75
    shipment
    -0.74
    قسم
    -0.73
    скет
    -0.71
    Pkt
    -0.70
    Cause
    -0.70
    recursion
    -0.69
    Shipping
    -0.69
    है
    -0.68
    POSITIVE LOGITS
    teck
    0.79
    又
    0.77
    cave
    0.73
     combien
    0.73
    guma
    0.71
    щадь
    0.69
    ミルク
    0.68
     cave
    0.68
     clinicians
    0.67
     права
    0.66
    Activations Density 0.039%

    No Known Activations