© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14608
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    The neuron fires on the key content words that introduce or label steps, timings, or user‐addressing instructions in procedural or instructional text.

    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
     송
    0.73
    Provide
    0.68
     seguir
    0.67
     fornisce
    0.67
    щі
    0.67
    Dentro
    0.65
     sentir
    0.65
     Posting
    0.64
    Iniciar
    0.64
    ഞ്ഞ
    0.64
    POSITIVE LOGITS
    譜
    0.80
     откры
    0.76
     மனைவி
    0.76
     выпла
    0.75
    編成
    0.72
    гель
    0.71
    EventListener
    0.70
     ABO
    0.70
    ны
    0.70
    報導
    0.70
    Activations Density 0.001%

    No Known Activations