© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47051
    Prev
    Next
    INDEX
    Explanations

    Specific words followed by small tokens

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

    The neuron activates strongly on mentions of sports fixtures and their outcomes (e.g. match clashes, wins/losses, qualification results).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    貼り
    -0.87
    dotte
    -0.84
     impedir
    -0.84
    ئلة
    -0.84
    ISSUES
    -0.84
     jouent
    -0.84
    ihnachten
    -0.83
    alım
    -0.82
    icação
    -0.82
    etsen
    -0.82
    POSITIVE LOGITS
    ém
    1.04
    DESCRIPTION
    0.95
     yesterday
    0.93
    昨晚
    0.88
     hombres
    0.84
     continental
    0.84
    getIntent
    0.83
    ý
    0.82
     الجهاز
    0.82
     curtains
    0.82
    Activations Density 0.011%

    No Known Activations