© 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. 7298
    Prev
    Next
    INDEX
    Explanations

    lists in various languages

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

    The neuron fires on the main content nouns (often agents or objects) that carry a passage’s key topic.

    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
    0.81
    -
    0.76
     delta
    0.72
     micro
    0.70
     gentle
    0.70
    –
    0.70
     heck
    0.67
     strata
    0.67
     microbe
    0.67
     jack
    0.66
    POSITIVE LOGITS
     রহিল
    0.79
    是
    0.77
     jsou
    0.75
    췄
    0.74
    则是
    0.73
     është
    0.73
     Defts
    0.73
     werden
    0.72
     नहीं
    0.71
    的には
    0.71
    Activations Density 0.863%

    No Known Activations