© 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. 73759
    Prev
    Next
    INDEX
    Explanations

    question or exclamation

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

    The neuron fires on Japanese punctuation characters (e.g. “、” and “!”).

    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
    b
    -1.85
    ya
    -1.84
    ma
    -1.81
    ing
    -1.70
     ſever
    -1.66
     pérd
    -1.62
     campeón
    -1.62
    da
    -1.60
     مشاهده
    -1.59
     Atención
    -1.59
    POSITIVE LOGITS
     and
    2.75
     because
    2.02
     when
    1.81
     in
    1.79
     like
    1.71
    ).
    1.70
     There
    1.69
     only
    1.59
     while
    1.58
     without
    1.58
    Activations Density 0.002%

    No Known Activations