© 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. 34-GEMMASCOPE-RES-131K
    7. 49746
    Prev
    Next
    INDEX
    Explanations

    football player roles

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

    This neuron detects the segment in sports biographies where a player’s current role is stated—especially the phrasing “plays as a …” (and its adjacent linking verbs like “is” or “plays”).

    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
    ناسب
    -0.87
    Bigr
    -0.86
    miljø
    -0.83
    ┖
    -0.80
     DEVICES
    -0.79
     şi
    -0.79
    bigr
    -0.79
    няли
    -0.77
     και
    -0.77
     because
    -0.77
    POSITIVE LOGITS
     midfield
    0.96
     midfielder
    0.95
    ignition
    0.88
     gleichen
    0.82
     Netzwerk
    0.81
     offrant
    0.79
    icha
    0.79
     brou
    0.79
    ante
    0.78
     forward
    0.78
    Activations Density 0.007%

    No Known Activations