© 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. 2202
    Prev
    Next
    INDEX
    Explanations

    specific actions or properties

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

    The neuron flags numeric tokens—especially reference numbers, years, page/volume figures, and similar numeric identifiers in bibliographic or data contexts.

    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
    Uma
    0.79
    서
    0.78
    اكم
    0.77
    ए
    0.76
    คนที่
    0.75
    dear
    0.74
    띵
    0.74
    GetData
    0.73
    어
    0.73
    Ain
    0.73
    POSITIVE LOGITS
     jú
    0.86
     Özellikle
    0.82
     slechts
    0.80
     labai
    0.78
     quanh
    0.76
     özellikle
    0.76
     μεγά
    0.74
     Veuillez
    0.73
     Hvis
    0.73
     tranquille
    0.73
    Activations Density 0.000%

    No Known Activations