© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 782
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on text about placing bets (e.g. wagering maximum coins in casino games).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.43
    f
    0.42
    l
    0.34
    @
    0.33
    ד
    0.33
    ↵
    0.32
    ic
    0.32
    m
    0.32
    h
    0.32
    p
    0.32
    POSITIVE LOGITS
     suelen
    0.51
     calorías
    0.48
     empate
    0.47
     możesz
    0.46
     comerciantes
    0.45
     Betfair
    0.44
     estadounidenses
    0.44
    ബോ
    0.44
     joueurs
    0.43
     ofrecen
    0.43
    Activations Density 0.000%

    No Known Activations