© 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. 13108
    Prev
    Next
    INDEX
    Explanations

    pronunciation in parentheses or quotes

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

    The neuron is triggered by mathematical terminology and numeric expressions—words like “inverse,” “domain,” “range,” “equal,” “dividing,” numbers, and related symbols.

    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
    /
    1.17
     (
    0.99
     др
    0.85
     &
    0.84
      
    0.78
     :
    0.77
    （
    0.77
     ;
    0.73
    (
    0.72
    *;
    0.70
    POSITIVE LOGITS
     ähm
    1.45
     ờ
    1.20
     えっと
    1.18
     เอ่อ
    1.16
     uh
    1.13
     보면은
    1.13
     Mhm
    1.11
     เนาะ
    1.09
     diciamo
    1.07
     cetera
    0.97
    Activations Density 0.225%

    No Known Activations