© 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. 10131
    Prev
    Next
    INDEX
    Explanations

    start your

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

    The neuron activates on uppercase legal‐style labels and trademark or alert headings (e.g., “NOTICE,” “ALERT,” “trademarks”) in document metadata.

    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
     భూ
    1.02
    ங்கிணை
    0.82
     ಭೂ
    0.75
    야
    0.71
     العلم
    0.70
     대상
    0.70
    ныгы
    0.70
    ール
    0.69
    是对
    0.68
     공
    0.68
    POSITIVE LOGITS
     nonché
    0.76
    ?\\
    0.75
    ?!?
    0.73
    .'"
    0.71
    these
    0.69
    Estos
    0.68
    ?')
    0.68
     begonnen
    0.68
    .\\
    0.67
     pylori
    0.67
    Activations Density 0.000%

    No Known Activations