© 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. 78615
    Prev
    Next
    INDEX
    Explanations

    starter or starting role

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

    This neuron detects words referring to a sports player’s role, status, or team-related position.

    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
    Ранее
    -0.74
     そば
    -0.73
    Materiaal
    -0.72
    SetState
    -0.71
    officially
    -0.69
    Tudo
    -0.69
     Parity
    -0.69
    urro
    -0.68
     évo
    -0.68
     imageName
    -0.68
    POSITIVE LOGITS
     starting
    5.22
     starter
    4.94
     starters
    4.63
    starting
    4.06
    Starting
    4.03
     Starting
    3.94
    starter
    3.72
     Starter
    3.50
    Starter
    3.39
    STARTING
    3.06
    Activations Density 0.044%

    No Known Activations