© 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. 5553
    Prev
    Next
    INDEX
    Explanations

    `use` followed by `((`

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

    The neuron fires on numeric tokens (multi‐digit numbers, years, phone numbers, prices, etc.).

    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
     Pública
    0.55
    #/
    0.54
     Букмекерская
    0.53
    ZZ
    0.52
    Rot
    0.51
    öss
    0.51
     Materialien
    0.49
    ക്കുന്ന
    0.49
    Return
    0.49
    adero
    0.49
    POSITIVE LOGITS
     ((
    1.27
    ((
    1.22
    ',(
    1.07
    ",(
    1.02
     (((
    1.00
     async
    0.98
    >((
    0.96
    ":(
    0.93
    (([
    0.90
    =(
    0.89
    Activations Density 0.032%

    No Known Activations