© 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. 30406
    Prev
    Next
    INDEX
    Explanations

    2018 dates and names

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

    The neuron activates on numeric tokens—especially sports statistics like scores, counts, and game-related numbers.

    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
    Biden
    -1.80
     Biden
    -1.67
     pandemic
    -1.64
     omicron
    -1.61
     Covid
    -1.61
    Covid
    -1.59
     covid
    -1.58
     metaverse
    -1.56
     Omicron
    -1.52
     Wordle
    -1.45
    POSITIVE LOGITS
     GDPR
    1.88
     Brexit
    1.85
     Trump
    1.78
    Brexit
    1.76
    SaveSave
    1.59
    Trump
    1.57
    GDPR
    1.53
     Fortnite
    1.49
     ২০১
    1.39
     ۲۰۱
    1.36
    Activations Density 0.972%

    No Known Activations