© 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. 44875
    Prev
    Next
    INDEX
    Explanations

    Spike, spike trains, Spike TV, Spike Co

    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
    A
    -3.05
    l
    -2.94
     tragically
    -2.63
     stubbornly
    -2.50
    >
    -2.47
     perfectly
    -2.42
     instill
    -2.38
    ’
    -2.38
    re
    -2.36
     playfully
    -2.31
    POSITIVE LOGITS
    詒
    3.03
    鋱
    2.95
    geſ
    2.81
    鱨
    2.80
    genodigd
    2.64
     ideen
    2.61
     praktis
    2.59
    sekten
    2.58
    reiz
    2.55
    珰
    2.47
    Activations Density 0.002%

    No Known Activations