© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39488
    Prev
    Next
    INDEX
    Explanations

    terms in quotes

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

    This neuron responds to typographic (curly) quotation marks (the “ and ” characters) surrounding quoted phrases.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -3.05
    Karena
    -1.87
    كاتب
    -1.81
    Прият
    -1.73
    اريخ
    -1.73
    </h2>
    -1.71
    خبار
    -1.71
    卨
    -1.69
    Kalau
    -1.69
    Some
    -1.68
    POSITIVE LOGITS
     of
    6.28
     that
    2.95
     to
    2.83
    凄く
    1.70
     dando
    1.70
     schnelle
    1.69
     from
    1.66
     than
    1.65
     famoso
    1.64
     hochwertige
    1.62
    Activations Density 0.127%

    No Known Activations