© 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. 10-GEMMASCOPE-RES-131K
    4. 105193
    Prev
    Next
    INDEX
    Explanations

    athletics events

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

    The neuron responds to mentions of track and field athletics—especially specific event names or athlete roles (e.g. shot putter, long jumper, triple jumper).

    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
     its
    -1.60
    Its
    -1.35
     already
    -1.25
     ALREADY
    -1.23
     ситуация
    -1.22
     sembler
    -1.21
    已經
    -1.19
     existing
    -1.19
    already
    -1.16
    ที่มี
    -1.15
    POSITIVE LOGITS
    鏖
    1.45
    lename
    1.27
    requipa
    1.26
    Ϻ
    1.22
    הפ
    1.15
     начинают
    1.11
    ఏ
    1.11
    mazione
    1.10
     evidently
    1.10
    ramento
    1.10
    Activations Density 0.036%

    No Known Activations