© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12288
    Prev
    Next
    INDEX
    Explanations

    list delimiters or introductory words

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

    The neuron activates on numeric tokens—especially multi‐digit or decimal numbers (e.g. floating‐point 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
    erweise
    0.84
    ták
    0.82
    да
    0.78
    n
    0.75
    o
    0.74
    tions
    0.73
    sion
    0.73
    numeric
    0.73
    ic
    0.68
    t
    0.68
    POSITIVE LOGITS
     tritium
    0.96
     mundial
    0.88
     embezzlement
    0.85
     fudai
    0.83
    दे
    0.82
     leyes
    0.81
     ridurre
    0.81
    मौ
    0.80
     prilikom
    0.80
    饮食
    0.80
    Activations Density 0.000%

    No Known Activations