© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12217
    Prev
    Next
    INDEX
    Explanations

    drive ins, dives, assessments, creation

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

    The neuron activates on floating-point numeric tokens (numbers containing a decimal point).

    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
     "
    0.68
    </strong>
    0.66
     a
    0.66
     ♦
    0.65
     그
    0.63
     Rik
    0.63
    아
    0.63
     또한
    0.62
     volunteer
    0.62
     DAY
    0.62
    POSITIVE LOGITS
    zonych
    0.95
     количеством
    0.93
     настолько
    0.90
     расположение
    0.90
    rjust
    0.89
    ള്ള
    0.88
     годах
    0.88
    gadas
    0.86
     хоть
    0.86
    реги
    0.86
    Activations Density 0.000%

    No Known Activations