© 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. 15903
    Prev
    Next
    INDEX
    Explanations

    compliance department

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

    The neuron fires on long, uncommon multi‐syllabic words—especially technical or Latinate terms with suffixes like –ive, –otic, –olus, etc.

    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
    𝙚
    0.80
    amı
    0.75
     tropes
    0.73
     ………………………………..
    0.69
    iques
    0.67
    ୍
    0.67
     Sénégal
    0.66
     Séance
    0.66
    тни
    0.64
     proches
    0.64
    POSITIVE LOGITS
    至於
    0.91
    debate
    0.86
    検査
    0.77
    story
    0.76
    station
    0.75
    apuris
    0.75
    Ｇ
    0.74
    scenario
    0.73
    vider
    0.73
     ടീ
    0.73
    Activations Density 0.000%

    No Known Activations