© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45333
    Prev
    Next
    INDEX
    Explanations

    scoring points in games

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

    This neuron detects sports‐style scoring or statistical lines, i.e. mentions of “scored,” “scores,” “tallied,” etc., paired with numeric game statistics.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    1
    -0.93
    pora
    -0.89
    事を
    -0.88
    mathrm
    -0.87
     miſ
    -0.85
    嚴
    -0.85
    事が
    -0.85
    kespeare
    -0.85
     стро
    -0.84
     completamente
    -0.84
    POSITIVE LOGITS
     in
    1.49
     on
    1.29
     from
    1.25
     gång
    1.05
     twice
    1.04
     first
    1.02
     loopt
    1.00
     during
    0.98
     against
    0.98
     arba
    0.93
    Activations Density 0.011%

    No Known Activations