© 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. 85131
    Prev
    Next
    INDEX
    Explanations

    betting, gambling, or playing

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

    The neuron strongly activates on words related to betting or gambling (“bet,” “wager,” “gamble,” 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
    ⼥
    -1.74
    leine
    -1.73
     pério
    -1.67
     doar
    -1.55
     walmart
    -1.54
    dersfield
    -1.53
    gifter
    -1.52
     évent
    -1.51
     chinese
    -1.49
     ため
    -1.49
    POSITIVE LOGITS
    СЫ
    1.57
    s
    1.55
    ubourg
    1.54
    einander
    1.48
    $,
    1.43
    FieldNumber
    1.42
    up
    1.41
     cũng
    1.41
    iliares
    1.41
     entanto
    1.37
    Activations Density 0.024%

    No Known Activations