© 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. 77298
    Prev
    Next
    INDEX
    Explanations

    technical, programming, or numerical notation

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

    The neuron fires on sports‐context proper nouns and jargon—especially team names, player names, venues, and game details.

    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
     two
    -1.28
     many
    -1.23
     noticeably
    -1.12
     one
    -1.10
     seemingly
    -1.08
     sophisticated
    -1.07
     sizable
    -1.07
     three
    -1.05
     some
    -1.00
     does
    -1.00
    POSITIVE LOGITS
     Dinas
    1.05
     oef
    1.00
     UNDER
    0.97
     OX
    0.95
    recent
    0.94
     ultime
    0.94
     dins
    0.93
    covering
    0.93
     WIL
    0.91
    latest
    0.90
    Activations Density 0.004%

    No Known Activations