© 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. 186
    Prev
    Next
    INDEX
    Explanations

    This neuron primarily detects numeric tokens and figures (e.g. years, decimal numbers, large numerals) in the text.

    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
     two
    0.53
    0.50
     sierp
    0.50
     starboard
    0.49
     schwarzen
    0.47
    สอง
    0.47
    Two
    0.47
    只
    0.46
    就是
    0.46
     Two
    0.46
    POSITIVE LOGITS
     psychosocial
    0.72
     policymakers
    0.71
     socioeconomic
    0.67
     advocacy
    0.65
     социально
    0.63
     macroeconomic
    0.63
     mismanagement
    0.63
     policym
    0.62
     rulemaking
    0.62
     geospatial
    0.59
    Activations Density 0.465%

    No Known Activations