© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9709
    Prev
    Next
    INDEX
    Explanations

    website sections or links

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

    The neuron flags tokens that are part of web addresses or file‐path URLs (e.g. domain names, slashes, and filename extensions).

    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
     due
    0.67
    /
    0.62
    6
    0.61
    /@
    0.60
    /+
    0.59
    grained
    0.58
     angiogenic
    0.58
     two
    0.56
    3
    0.56
    imation
    0.56
    POSITIVE LOGITS
     Newsletter
    0.73
     pdf
    0.72
     html
    0.69
    Publications
    0.66
     newsletter
    0.65
     اخبار
    0.65
     Pdf
    0.64
     Homepage
    0.62
    の話
    0.62
    dataFile
    0.62
    Activations Density 0.017%

    No Known Activations