© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15663
    Prev
    Next
    INDEX
    Explanations

    close-knit community

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

    The neuron responds to hyphens (dash separators) in hyphenated compounds.

    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_31_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
    extré
    0.66
    encerramento
    0.66
    ॕ
    0.62
    một
    0.60
    Choisissez
    0.59
    valment
    0.59
    Nếu
    0.59
    Além
    0.59
    Été
    0.59
    établ
    0.58
    POSITIVE LOGITS
     yang
    0.64
     de
    0.63
     pada
    0.60
     dari
    0.59
     da
    0.59
     v
    0.57
     der
    0.57
     se
    0.57
     di
    0.57
     the
    0.57
    Activations Density 0.000%

    No Known Activations