© 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. 11359
    Prev
    Next
    INDEX
    Explanations

    violating your personal space

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

    The neuron fires most strongly on content words that describe key actions or events (especially action verbs and participles) in a sentence.

    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
    出来る
    0.81
     unscrupulous
    0.81
    ানোর
    0.75
     aiutare
    0.75
     comedic
    0.75
    選手の
    0.75
    ເພື່ອ
    0.75
     personagem
    0.74
    の為
    0.74
     perishable
    0.73
    POSITIVE LOGITS
    、
    0.78
    ､
    0.73
    ：
    0.70
    ः
    0.70
     bốn
    0.68
    両
    0.68
     、
    0.67
    và
    0.67
     국
    0.65
    했고
    0.64
    Activations Density 22.438%

    No Known Activations