© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3026
    Prev
    Next
    INDEX
    Explanations

    record, google, database, etc

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

    The neuron fires on the very first substantive token in each new text segment (i.e. the opening content word right after a segment boundary).

    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
     H
    0.75
    unga
    0.75
    #
    0.75
    ֔
    0.74
    ung
    0.73
     L
    0.72
    {
    0.72
     R
    0.71
     N
    0.71
    հ
    0.71
    POSITIVE LOGITS
    вшего
    0.78
     Coxeter
    0.75
    மல்ல
    0.73
    ренного
    0.73
    timeStamp
    0.72
     लक्षणों
    0.71
     doenças
    0.71
    ته
    0.70
     solutes
    0.70
     sulfides
    0.70
    Activations Density 0.000%

    No Known Activations