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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49708
    Prev
    Next
    INDEX
    Explanations

    fear and awe

    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
     Teddy
    -0.80
    mereka
    -0.78
     refill
    -0.78
    ляются
    -0.77
     /\.(
    -0.75
     jars
    -0.75
     породы
    -0.75
     Apa
    -0.75
    effort
    -0.74
    rétaire
    -0.73
    POSITIVE LOGITS
     trembling
    0.97
     precautions
    0.82
     crainte
    0.76
     bát
    0.75
     uncertainty
    0.73
    uncertainty
    0.72
     facing
    0.72
     wee
    0.70
    hnung
    0.70
     dt
    0.70
    Activations Density 0.017%

    No Known Activations