© 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. 5505
    Prev
    Next
    INDEX
    Explanations

    OCR engine

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

    The neuron detects decimal-formatted numerical identifiers (e.g. floating-point numbers like journal ISSN or DOI codes).

    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
    0.77
     :
    0.74
     (
    0.72
    A
    0.66
     $(
    0.65
    با
    0.65
    آ
    0.65
    ?!
    0.65
    $(
    0.64
    I
    0.64
    POSITIVE LOGITS
     राहुल
    0.94
     Aś
    0.90
     prebiotic
    0.90
     ortodox
    0.89
    मणि
    0.88
     доход
    0.87
     Kaspersky
    0.87
     umbilical
    0.86
    нося
    0.86
     coerc
    0.85
    Activations Density 0.006%

    No Known Activations