© 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. 65442
    Prev
    Next
    INDEX
    Explanations

    Surgical site infection rates

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

    references to Washington Redskins football team.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron activates on numeric tokens—years, scores, counts, and ordinals (e.g. “1920,” “33rd,” “28th”)—especially in sports season and game 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
    Baltimore
    -1.02
     Baltimore
    -0.79
    ająca
    -0.75
     añadió
    -0.73
    áním
    -0.72
     Freezer
    -0.71
     Assam
    -0.70
    ンドル
    -0.70
    Crab
    -0.70
    ᄂ
    -0.70
    POSITIVE LOGITS
     Delhi
    1.08
     Alexandria
    0.82
    Delhi
    0.79
    ultura
    0.75
     Ottawa
    0.75
     Brasília
    0.73
     Dirichlet
    0.72
     methodological
    0.72
     radiotherapy
    0.72
     け
    0.71
    Activations Density 0.014%

    No Known Activations