© 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. 34-GEMMASCOPE-RES-131K
    7. 30661
    Prev
    Next
    INDEX
    Explanations

    games in a row

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

    The neuron detects numeric stat figures (cardinal and ordinal numbers) in sports-related contexts.

    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
    どちらも
    -0.87
     некоторых
    -0.86
     decades
    -0.82
    arschijnlijk
    -0.79
     еще
    -0.77
    ױ
    -0.77
    ✏
    -0.76
     beberapa
    -0.76
     görün
    -0.76
     ilan
    -0.75
    POSITIVE LOGITS
     five
    1.10
     seven
    1.03
     four
    1.03
     our
    0.99
     games
    0.98
     outings
    0.97
     six
    0.97
     their
    0.95
     sieben
    0.92
    getLast
    0.92
    Activations Density 0.018%

    No Known Activations