© 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. 11940
    Prev
    Next
    INDEX
    Explanations

    important disclaimer

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

    The neuron selectively activates on the stems of longer, multi-syllabic words (often of Latinate or complex derivational structure).

    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
    ний
    0.83
    довой
    0.65
    ový
    0.64
    1
    0.64
    6
    0.63
    kový
    0.63
    astian
    0.62
    tfrac
    0.59
    undering
    0.59
    0
    0.59
    POSITIVE LOGITS
    ങ്ങളിൽ
    0.75
    enaries
    0.74
     khususnya
    0.73
     such
    0.71
     несмотря
    0.71
     malgré
    0.70
    וחות
    0.68
     മറ്റു
    0.67
     zarówno
    0.67
     तेलंगाना
    0.66
    Activations Density 0.448%

    No Known Activations