© 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. 9545
    Prev
    Next
    INDEX
    Explanations

    / with separators

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

    The neuron strongly activates on numeric tokens representing quantitative values (e.g. measurements, statistics, citation numbers), essentially detecting numbers.

    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
    es
    0.79
    ys
    0.76
     laborales
    0.73
     har
    0.70
     apprentices
    0.68
    izowane
    0.67
    淸
    0.67
    ulkar
    0.66
     sillons
    0.66
     activités
    0.64
    POSITIVE LOGITS
    譏
    0.78
    カー
    0.75
    ньому
    0.74
    ভেট
    0.73
    THING
    0.73
    OSPH
    0.71
    This
    0.70
     Ihr
    0.70
    Simulator
    0.69
     granule
    0.69
    Activations Density 0.000%

    No Known Activations