© 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. 31-GEMMASCOPE-2-RES-16K
    4. 8383
    Prev
    Next
    INDEX
    Explanations

    function definition or call

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

    The neuron fires on numeric tokens and numerical expressions (e.g. standalone numbers, measurements, or coded number sequences).

    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_31_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
     vždy
    0.68
     {
    0.60
     sempre
    0.60
     zawsze
    0.59
     {}
    0.57
     manne
    0.57
     Advocacy
    0.57
     =
    0.56
     vedno
    0.55
     always
    0.55
    POSITIVE LOGITS
    kA
    0.69
     کردند
    0.64
    schod
    0.59
    сколько
    0.59
    getPosition
    0.58
    *",
    0.58
    প্রকার
    0.58
    ]|
    0.57
    putation
    0.57
    Hmm
    0.56
    Activations Density 0.000%

    No Known Activations