© 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. 26204
    Prev
    Next
    INDEX
    Explanations

    game wins and victories

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

    The neuron detects numeric game scores (e.g. “34-20,” “5-1,” “85-73”) and related victory/ win mentions.

    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
    对于
    -1.09
    Record
    -1.04
    夏天
    -0.96
    基于
    -0.95
    Suddenly
    -0.94
    ();
    -0.91
    Geometry
    -0.91
    ılacak
    -0.91
    VER
    -0.90
     segala
    -0.90
    POSITIVE LOGITS
    ישה
    1.09
    Dise
    1.09
    Forme
    1.07
    Crédit
    1.02
    wijl
    1.02
     molto
    1.02
    Litter
    1.00
    Tobi
    0.99
    してくれた
    0.99
     FELLOW
    0.99
    Activations Density 0.010%

    No Known Activations