© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47452
    Prev
    Next
    INDEX
    Explanations

    sports contexts

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

    The neuron is acting as a general verb detector, flagging non‐“-ing” verb forms (including infinitives, base forms, and finite verbs) wherever they occur.

    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
    Salmonella
    -0.77
     Chore
    -0.75
    Geografi
    -0.75
    ska
    -0.69
    CHM
    -0.65
     Arra
    -0.65
    hringer
    -0.65
    ṯ
    -0.65
     Tactics
    -0.65
    glPopMatrix
    -0.65
    POSITIVE LOGITS
     sports
    5.84
     sport
    4.69
    sports
    4.38
     sporting
    4.19
     athletic
    4.03
     Sports
    3.92
    Sports
    3.81
    sport
    3.73
     sporty
    3.63
     SPORTS
    3.63
    Activations Density 0.157%

    No Known Activations