© 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. 7814
    Prev
    Next
    INDEX
    Explanations

    lists and formatting

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

    This neuron activates on sequences of uppercase letters or title‐style words—i.e. headings, all-caps brand/product names, or headline tokens.

    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
     tersebut
    0.83
    .\"
    0.77
    .)
    0.75
     moieties
    0.75
     pertaining
    0.73
     heretofore
    0.72
     embodiments
    0.70
    .}
    0.70
     अथवा
    0.70
     desirous
    0.70
    POSITIVE LOGITS
     जानिए
    0.93
     kvůli
    0.83
    coronavirus
    0.82
     coronavirus
    0.81
    Coronavirus
    0.81
     Coronavirus
    0.79
     Reveals
    0.79
     বিপজ্জনক
    0.77
     incroyable
    0.76
     Putin
    0.74
    Activations Density 0.155%

    No Known Activations