© 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. 6184
    Prev
    Next
    INDEX
    Explanations

    punctuation and separators

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

    The neuron strongly activates on proper names and other named-entity tokens (e.g. brands, companies, organizations).

    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
     근데
    0.86
    ábamos
    0.82
    чё
    0.81
    وضح
    0.77
     കൊടു
    0.77
    fromi
    0.77
    𝚌
    0.77
     তৈরী
    0.76
    腟
    0.75
    idenav
    0.75
    POSITIVE LOGITS
     www
    0.75
     L
    0.69
     deliberately
    0.68
    ,
    0.67
     entrer
    0.65
     M
    0.64
     also
    0.63
     R
    0.63
     and
    0.62
     S
    0.62
    Activations Density 0.013%

    No Known Activations