© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15876
    Prev
    Next
    INDEX
    Explanations

    code separators

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

    The neuron strongly activates on numeric tokens—digits and decimal points—i.e. it detects numbers (especially in decimal/scientific notation).

    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_31_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
    ='
    0.75
    ="
    0.68
     =
    0.67
    =@
    0.64
    =(
    0.62
    =("
    0.61
    =
    0.60
     :=
    0.59
     isEmpty
    0.59
     i
    0.58
    POSITIVE LOGITS
     では
    0.59
     Lad
    0.57
     Sied
    0.57
     सुख
    0.56
    പ്പെടുന്ന
    0.56
     Künst
    0.56
     Onder
    0.56
     Secundaria
    0.56
     Văn
    0.55
    णासाठी
    0.55
    Activations Density 0.000%

    No Known Activations