© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12538
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on mentions of “risk” (especially in quantified or “risk of” contexts).

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

    the phrase "risk of" in contexts discussing potential dangers or hazards.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of risk or danger, especially constructions discussing the “risk of” something and efforts to reduce or manage that risk.

    oai_token-act-pair · gpt-5Triggered 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
     impervious
    1.00
    কারের
    0.98
     Shelter
    0.98
     withstand
    0.95
     şart
    0.95
    WCHAR
    0.95
     negatively
    0.94
     ochr
    0.94
     eas
    0.93
     PROTECTION
    0.92
    POSITIVE LOGITS
    ל
    1.24
    фи
    1.05
    ש
    1.05
    风险
    1.03
    ח
    1.01
    Risk
    1.00
    री
    0.99
     Risk
    0.98
    我
    0.97
    ги
    0.97
    Activations Density 0.100%

    No Known Activations