© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 15891
    Prev
    Next
    INDEX
    Explanations

    SvelteKit components

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

    The neuron is primarily triggered by numeric values (especially floating-point numbers) in the text.

    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
    ರೆ
    0.76
    OPTIONS
    0.75
    ﻩ
    0.75
     不同
    0.73
    THING
    0.72
     nourrice
    0.71
    cInfo
    0.71
    ب
    0.71
    餑
    0.71
    UMS
    0.70
    POSITIVE LOGITS
     debuts
    0.70
    idez
    0.68
     دیدار
    0.68
     جوان
    0.68
     فعل
    0.67
     Avery
    0.66
    hidupan
    0.66
     cenderung
    0.66
     Claremont
    0.65
     vias
    0.65
    Activations Density 0.000%

    No Known Activations