© 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. 1297
    Prev
    Next
    INDEX
    Explanations

    for loop opening parenthesis

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

    The neuron detects numeric tokens (numbers, including decimals) 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
    t
    0.65
    ح
    0.64
    té
    0.63
    NOV
    0.62
    mét
    0.62
    ä
    0.62
    ní
    0.60
    ं
    0.60
    niveau
    0.59
    售后
    0.59
    POSITIVE LOGITS
     Ци
    0.66
    permutation
    0.60
     лам
    0.54
     Mentre
    0.54
     방정식
    0.52
     стрельца
    0.52
     assertTrue
    0.52
     উল্লেখ
    0.52
     nDims
    0.52
     ਜ਼
    0.52
    Activations Density 0.000%

    No Known Activations