© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5444
    Prev
    Next
    INDEX
    Explanations

    a bit of

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

    The neuron is keyed to detect numbered list or section markers (e.g. parenthesized numerals like “(2)” or “(3)”) indicating enumerated items.

    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
    codehaus
    0.73
    Bool
    0.72
    <0xE0>
    0.72
    Rpc
    0.72
    ясплат
    0.71
    mathbf
    0.71
    ″]
    0.71
    க
    0.70
     insurrection
    0.70
     inoculum
    0.68
    POSITIVE LOGITS
     suur
    0.73
     gasket
    0.73
     Είναι
    0.72
     قیمت
    0.71
     Dimensional
    0.71
     dimensional
    0.70
    ﯿ
    0.70
     salad
    0.69
    ﯼ
    0.69
    quist
    0.68
    Activations Density 0.001%

    No Known Activations