© 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. 12471
    Prev
    Next
    INDEX
    Explanations

    area of

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

    The neuron fires whenever it sees a numeric quantity (especially decimal-format measurements or computed 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
    Income
    0.74
    Handsome
    0.71
     หลัก
    0.68
     जिससे
    0.66
     {}'.
    0.66
    FORMANCE
    0.65
     demikian
    0.64
    Normalized
    0.64
    Colorado
    0.63
     toJson
    0.63
    POSITIVE LOGITS
     of
    0.91
    aps
    0.89
    ática
    0.88
     ofthe
    0.85
    ofthe
    0.79
     của
    0.77
    ofs
    0.77
     Of
    0.73
    々の
    0.73
    㡀
    0.72
    Activations Density 0.001%

    No Known Activations