© 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. 6387
    Prev
    Next
    INDEX
    Explanations

    math operators and numbers

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

    The neuron activates on numeric tokens (numbers and arithmetic values) 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_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
    MessageBox
    0.63
    DEBUG
    0.61
    ขณะ
    0.59
    ักษณะ
    0.59
    ^*(\
    0.59
     ingress
    0.59
    DBGPRINT
    0.59
     freq
    0.58
    lVert
    0.58
     diagnostics
    0.58
    POSITIVE LOGITS
     Treasurer
    0.83
     treasurer
    0.77
     of
    0.70
    chool
    0.69
     Farmers
    0.69
    ounty
    0.68
     Samantha
    0.68
     ______
    0.68
     keinginan
    0.67
    ारी
    0.67
    Activations Density 0.008%

    No Known Activations