© 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. 11370
    Prev
    Next
    INDEX
    Explanations

    Boolean OR operator

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

    The neuron fires most strongly on low‐frequency, content‐heavy tokens (i.e. unusually rare or “surprising” words).

    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
    پیش
    0.87
    ċ
    0.86
    :'',
    0.83
    ะ
    0.80
    рь
    0.80
    yards
    0.79
     heterosexual
    0.79
    '.$
    0.79
    طرف
    0.79
     tedav
    0.78
    POSITIVE LOGITS
     ایمان
    0.72
     Peace
    0.71
     Simultaneous
    0.71
     Sovere
    0.70
     Observatory
    0.69
     Acoustics
    0.69
    iances
    0.68
    ihilation
    0.68
     Guerre
    0.67
    ooker
    0.67
    Activations Density 0.001%

    No Known Activations