© 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. 3036
    Prev
    Next
    INDEX
    Explanations

    French/Spanish "shadow"

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

    The neuron spotlights numeric literals (especially floating-point values) appearing 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_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
    getattr
    0.73
     getattr
    0.72
    ((
    0.70
     [(
    0.68
    [(
    0.65
    [],
    0.63
    ={`
    0.61
    {
    0.61
     +=
    0.60
    ('',
    0.60
    POSITIVE LOGITS
     disebut
    0.77
    चाकी
    0.77
     君
    0.75
     Très
    0.73
     GÉN
    0.73
     nazy
    0.72
     काळजी
    0.71
    ेंद्रीय
    0.70
     bistouri
    0.70
     म्हटले
    0.69
    Activations Density 0.005%

    No Known Activations