© 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. 13820
    Prev
    Next
    INDEX
    Explanations

    negative descriptions or outcomes

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

    This neuron activates strongly on long, multisyllabic content words (e.g. “symptoms,” “reluctance,” “emergency,” “protocol,” “instantly,” etc.).

    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
    /
    0.99
     (
    0.96
    (
    0.78
     इत्यादि
    0.78
     Итак
    0.78
     Something
    0.72
     Thus
    0.71
     Announces
    0.71
     इत्यादी
    0.71
     This
    0.69
    POSITIVE LOGITS
    跟他
    0.69
     unwitting
    0.67
    гант
    0.67
     cocaine
    0.66
    拿着
    0.66
     folosit
    0.66
     ­
    0.64
    뺨
    0.64
     कथित
    0.63
    を使う
    0.63
    Activations Density 0.005%

    No Known Activations