© 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. 14408
    Prev
    Next
    INDEX
    Explanations

    describe later, format spec

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

    The neuron is keyed to numeric sequences—identifying tokens that are part of numbers (dates, amounts, phone numbers, percentages, etc.).

    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
    lmfit
    0.94
    themem
    0.92
     эмне
    0.90
    clientsdetails
    0.89
    忶
    0.89
    diendo
    0.87
     ٹینس
    0.85
    데이터
    0.85
    ທີ່
    0.84
     ойношот
    0.84
    POSITIVE LOGITS
    ’
    0.83
    c
    0.79
     lately
    0.74
     dinner
    0.74
    s
    0.73
    x
    0.73
     j
    0.71
     dinners
    0.71
     C
    0.69
    q
    0.69
    Activations Density 0.006%

    No Known Activations