© 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. 16232
    Prev
    Next
    INDEX
    Explanations

    entering your nostrils

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

    The neuron fires on named entities and specific proper‐noun tokens—e.g. place names, organization or product names, street names, link labels, dates, 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
     書い
    0.91
     andRow
    0.86
     聞い
    0.80
    کروچ
    0.80
    spacePad
    0.79
     toplant
    0.79
     Dadurch
    0.79
    纂
    0.77
     expliqué
    0.77
     遊ん
    0.76
    POSITIVE LOGITS
    0.93
     maze
    0.84
    6
    0.80
    যত
    0.79
    ID
    0.76
    пси
    0.73
     log
    0.73
    문
    0.73
    Type
    0.71
     complex
    0.71
    Activations Density 0.003%

    No Known Activations