© 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. 22-GEMMASCOPE-RES-131K
    7. 13834
    Prev
    Next
    INDEX
    Explanations

    career-high or records

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

    The neuron detects mentions of athletic or performance statistical highs and records (e.g., “career-high,” “season-high,” “record”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    illaries
    -1.13
    estries
    -1.08
     gedeelte
    -1.06
     ändert
    -1.03
     Our
    -1.00
    anmar
    -0.99
     hvilket
    -0.99
    UrlEncoded
    -0.98
    taminophen
    -0.98
     beinhaltet
    -0.98
    POSITIVE LOGITS
     Saltar
    1.20
     يساعد
    1.13
     Evangelio
    1.09
    ⅞
    1.08
    waarden
    1.01
     pasien
    1.01
    ținut
    1.00
     professionelle
    1.00
     другую
    0.98
    ==='
    0.98
    Activations Density 0.009%

    No Known Activations