© 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. 22-GEMMASCOPE-RES-131K
    7. 13928
    Prev
    Next
    INDEX
    Explanations

    events, scores, and winning

    np_acts-logits-general · gemini-2.5-flash-lite

    the neuron fires on mentions of game outcomes—words and phrases signaling wins, losses, and streaks.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    mostly
    -1.19
     largely
    -1.18
    mainly
    -1.11
     exceptionally
    -1.07
     abſ
    -1.02
     daer
    -1.02
     vong
    -1.02
     graden
    -1.02
     biss
    -1.02
     kard
    -1.02
    POSITIVE LOGITS
     in
    1.67
     during
    1.55
     while
    1.43
     three
    1.27
     before
    1.26
     after
    1.20
     when
    1.17
     four
    1.15
     any
    1.15
     since
    1.10
    Activations Density 0.021%

    No Known Activations