© 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. 22-GEMMASCOPE-RES-131K
    7. 129424
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly fires on the closing delimiter of block comments (“*/”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    programming and technical 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_22/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
     in
    -1.37
     to
    -1.19
     (
    -1.16
     only
    -1.09
     people
    -1.07
     November
    -1.07
     !!!
    -1.04
     by
    -1.03
     April
    -1.03
     comes
    -1.02
    POSITIVE LOGITS
     verschillen
    1.28
     EIF
    1.25
    Etape
    1.24
     affor
    1.23
     sellado
    1.22
    Trabaj
    1.18
     trám
    1.18
     toutefois
    1.18
     déplacements
    1.16
    感じです
    1.15
    Activations Density 0.000%

    No Known Activations