© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15859
    Prev
    Next
    INDEX
    Explanations

    into categories or sections

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

    The neuron detects tokens that express numeric quantities (e.g. spelled-out number words indicating counts or amounts).

    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
     each
    0.86
     EACH
    0.86
     Each
    0.78
    Each
    0.75
    each
    0.72
     各
    0.70
     jednotliv
    0.68
     각
    0.67
     hver
    0.66
     inch
    0.65
    POSITIVE LOGITS
     главное
    0.78
     haupt
    0.75
    distinct
    0.69
     बेसिकली
    0.69
     distinct
    0.68
    主要
    0.68
    principal
    0.66
     principalmente
    0.66
     grundsätzlich
    0.62
    为主
    0.60
    Activations Density 0.167%

    No Known Activations