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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45330
    Prev
    Next
    INDEX
    Explanations

    goalkeeper names

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

    The neuron strongly activates on mentions of goalkeepers (and related terms like “keeper,” “goalkeeper,” “goaltender,” “saves,” etc.).

    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
     rossa
    -0.84
    absorbing
    -0.81
     Graf
    -0.77
    Présentation
    -0.75
    defense
    -0.73
    毀
    -0.72
    șa
    -0.70
    紺
    -0.70
    veda
    -0.69
     diskusi
    -0.69
    POSITIVE LOGITS
     川
    0.82
    MONITOR
    0.80
     Ochoa
    0.79
     starter
    0.79
     Starter
    0.76
    墙壁
    0.75
     pedir
    0.74
     »,
    0.74
    üy
    0.73
     CÓ
    0.73
    Activations Density 0.014%

    No Known Activations