© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13170
    Prev
    Next
    INDEX
    Explanations

    3 in arithmetic

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

    This neuron detects imperial measurement dimensions, primarily numbers followed by quotes and “x” separators (e.g. 8" x 3" x 5").

    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
    =',
    0.50
     editText
    0.46
     =
    0.46
    )+
    0.46
    uffix
    0.43
    ishwarya
    0.43
     لیاقت
    0.42
    =$_
    0.41
     менен
    0.41
    ())+
    0.41
    POSITIVE LOGITS
     Gibb
    0.55
     Tasmanian
    0.47
     ఒక
    0.47
     прием
    0.45
     রং
    0.45
     игровые
    0.45
     toeg
    0.44
     Ats
    0.44
     इतर
    0.43
     AGA
    0.43
    Activations Density 0.015%

    No Known Activations