© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103568
    Prev
    Next
    INDEX
    Explanations

    sports phrases and outcomes

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

    The neuron activates on domain‐specific sports jargon—terms describing match events, player actions, and game conditions.

    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
     склад
    -0.76
     changelog
    -0.73
    OSE
    -0.72
    da
    -0.70
     Beyonce
    -0.69
     downright
    -0.69
    Tabla
    -0.69
    怕
    -0.69
     попа
    -0.68
    引き
    -0.67
    POSITIVE LOGITS
     merchant
    0.85
     adecu
    0.84
     Modèle
    0.83
    感じです
    0.82
    Mentor
    0.81
     çiz
    0.80
    gemeen
    0.79
    kosi
    0.79
     guadag
    0.79
    𝑈
    0.79
    Activations Density 0.025%

    No Known Activations