© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111398
    Prev
    Next
    INDEX
    Explanations

    sports leagues and tournaments

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

    The neuron fires on mentions of professional tennis tournament circuit classes or series names (e.g. “ATP Challenger,” “Futures,” “ITF”).

    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
     uyt
    -1.44
    ↵
    -1.21
     there
    -1.18
     by
    -1.16
     then
    -1.13
    <>
    -1.13
     weichen
    -1.10
    ЧИТА
    -1.09
     još
    -1.08
     AKA
    -1.07
    POSITIVE LOGITS
    EROS
    1.45
    ."
    1.40
    閲
    1.25
    poda
    1.20
     your
    1.12
     IMHO
    1.12
    都要
    1.10
    requisite
    1.09
    rafat
    1.09
     %.
    1.09
    Activations Density 0.044%

    No Known Activations