© 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. 7347
    Prev
    Next
    INDEX
    Explanations

    variable assignment with =

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

    The neuron fires on numeric tokens—i.e. it detects numbers (digits or numeric values) 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
    OHA
    0.70
    Nasdaq
    0.61
    Donc
    0.60
    NES
    0.59
     जाण
    0.55
    Przeczytaj
    0.54
    꽤
    0.54
     आश्च
    0.53
     चौंका
    0.53
    신의
    0.53
    POSITIVE LOGITS
     ,
    0.69
     textbox
    0.63
     ()
    0.62
     gazebo
    0.62
     misalkan
    0.61
     (),
    0.60
    ittura
    0.58
    pyridazine
    0.58
     misalnya
    0.57
     Cang
    0.56
    Activations Density 0.031%

    No Known Activations