© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44169
    Prev
    Next
    INDEX
    Explanations

    bang, banging, banger

    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_10/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
    噥
    -2.88
    晙
    -2.70
    嫫
    -2.59
    焄
    -2.55
    錞
    -2.39
     แต่
    -2.36
    蛧
    -2.28
    摃
    -2.27
    蕻
    -2.22
    霂
    -2.19
    POSITIVE LOGITS
    {
    2.27
    [
    2.22
     persiapan
    2.05
    涷
    2.05
    gezogen
    2.03
     clamor
    2.00
    糨
    2.00
    \\
    2.00
    -
    1.95
     stehenden
    1.95
    Activations Density 0.004%

    No Known Activations