© 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. 10464
    Prev
    Next
    INDEX
    Explanations

    usually typically ordinarily

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

    The neuron primarily detects numeric specifications and measurements (e.g. quantities, dimensions, capacities, prices).

    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
     myself
    0.75
     our
    0.61
     my
    0.61
     съм
    0.57
     ·
    0.56
     ireland
    0.56
     www
    0.55
    能夠
    0.55
    我的
    0.54
    |
    0.53
    POSITIVE LOGITS
    avacan
    0.69
    قان
    0.67
     Mikolai
    0.67
    ℂ
    0.67
    тон
    0.66
    čit
    0.66
     Leibn
    0.66
    рте
    0.66
    refundable
    0.65
    cultured
    0.64
    Activations Density 0.397%

    No Known Activations