© 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. 99279
    Prev
    Next
    INDEX
    Explanations

    sports actions and roles

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

    This neuron detects mentions of on-field movement or positioning actions (e.g. run, spin, cut, motion, inside/outside, corner).

    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
    OpenGL
    -0.85
    ərbaycan
    -0.81
    𝗕
    -0.79
    HIDDEN
    -0.79
    Switzerland
    -0.77
    khó
    -0.77
     RAND
    -0.77
     разрабо
    -0.77
     comor
    -0.77
     Krakowie
    -0.77
    POSITIVE LOGITS
    的概念
    0.88
     concept
    0.84
     concepts
    0.79
     reads
    0.79
    ↶
    0.79
     coverage
    0.77
     their
    0.77
     responsibility
    0.75
     leveraging
    0.75
     your
    0.74
    Activations Density 0.009%

    No Known Activations