© 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. 10-GEMMASCOPE-RES-131K
    7. 69319
    Prev
    Next
    INDEX
    Explanations

    keywords followed by specific context

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

    The neuron fires strongly on the names of bookmakers and betting sites (e.g. Pinnacle, William Hill, Betfair, Five Dimes, Sports Interaction, 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_10/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
     without
    -1.58
     working
    -1.49
     already
    -1.34
     materials
    -1.30
     of
    -1.27
     work
    -1.23
     was
    -1.17
     iconLine
    -1.12
    +\
    -1.12
     products
    -1.11
    POSITIVE LOGITS
     you
    1.77
    🖌
    1.40
     आपको
    1.39
     silang
    1.38
     silikon
    1.23
    笑了笑
    1.23
    sieger
    1.21
    ándote
    1.21
    licopter
    1.21
     YOU
    1.21
    Activations Density 0.034%

    No Known Activations