© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130580
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on words naming music events and their details—venues, dates, tickets, lineups, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    events and venues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     вокруг
    -1.34
     using
    -1.18
    ଵ
    -1.18
    ଷ
    -1.18
    <em>
    -1.17
    ąp
    -1.16
    ⅛
    -1.16
     建設
    -1.12
     systemctl
    -1.11
     équipes
    -1.09
    POSITIVE LOGITS
    voer
    1.66
     accepte
    1.43
    openhauer
    1.39
     nesse
    1.36
    Последние
    1.35
     alumni
    1.31
     akik
    1.31
     sintomas
    1.30
     subió
    1.30
    ertale
    1.28
    Activations Density 0.044%

    No Known Activations