© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1601
    Prev
    Next
    INDEX
    Explanations

    quoted text or foreign language

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

    The neuron fires on numeric tokens—identifying numbers (e.g. monetary amounts, percentages, survey figures, and other numeric values).

    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_24_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
     vibr
    0.68
     &
    0.66
     levels
    0.66
     your
    0.64
     knives
    0.64
     projectiles
    0.63
     loops
    0.63
     textures
    0.62
     surfaces
    0.62
     datasets
    0.62
    POSITIVE LOGITS
    ."[
    0.64
    ."'
    0.63
     войне
    0.62
    .""
    0.60
     обосно
    0.57
    ？”
    0.57
     Такой
    0.57
    Então
    0.57
    ."
    0.56
    。"
    0.56
    Activations Density 0.000%

    No Known Activations