© 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. 5590
    Prev
    Next
    INDEX
    Explanations

    MAM, C, Catan, elf, rider, influence, Brains, cats, inherited

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

    This neuron detects mentions of casino or gambling games (especially slot machines and poker).

    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
     exact
    0.68
    }}
    0.67
    ه‌ها
    0.65
     potp
    0.64
    1
    0.64
     REQUIRED
    0.62
    emens
    0.62
    ه‌ای
    0.62
     required
    0.60
    izons
    0.60
    POSITIVE LOGITS
    <unused52>
    0.93
    ร้อม
    0.93
    kých
    0.88
    restrial
    0.86
    жают
    0.86
    arı
    0.85
    kana
    0.84
    гих
    0.84
    าด
    0.83
    เอียด
    0.83
    Activations Density 0.011%

    No Known Activations