© 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. 12938
    Prev
    Next
    INDEX
    Explanations

    form or previous

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

    The neuron fires strongly on the first prominent “content” word of each new text snippet or section, effectively flagging the opening keyword of each paragraph or segment.

    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
    ס
    0.91
    ্লিশ
    0.85
    de
    0.82
    гор
    0.76
    を用意
    0.76
    事實
    0.76
    VPS
    0.75
    د
    0.74
    서
    0.74
    क
    0.73
    POSITIVE LOGITS
    gomery
    0.74
     ဆ
    0.73
    oxone
    0.72
     calomel
    0.71
    NaBH
    0.69
    igroup
    0.69
    informatics
    0.69
    ো
    0.68
    ِه
    0.67
    ieno
    0.67
    Activations Density 0.000%

    No Known Activations