© 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. 10-GEMMASCOPE-RES-131K
    7. 102117
    Prev
    Next
    INDEX
    Explanations

    names of famous athletes

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

    The neuron strongly activates on the surnames of well‐known athletes, i.e. proper names of famous sports stars.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     like
    -1.89
     can
    -1.85
     of
    -1.82
     auf
    -1.80
     if
    -1.73
     for
    -1.71
     If
    -1.70
    ?
    -1.68
     *
    -1.67
     /
    -1.67
    POSITIVE LOGITS
     メニュー
    1.63
    ギュア
    1.55
    戗
    1.53
    ñera
    1.53
     améliorer
    1.52
     内衣
    1.51
    értel
    1.48
    蟶
    1.47
    翾
    1.47
    methoden
    1.46
    Activations Density 0.019%

    No Known Activations