© 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. 22-GEMMASCOPE-RES-131K
    4. 26776
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings after punctuation

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

    The neuron fires most strongly on the key subject words in a question’s title or header (e.g. folder names, file paths, or leading question words) to pick out the main topic of the query.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     then
    -1.37
    Then
    -1.26
    THEN
    -1.23
     and
    -1.15
    Moreover
    -1.14
     THEN
    -1.13
    ㄞ
    -1.10
     мои
    -1.09
    iric
    -1.09
    then
    -1.09
    POSITIVE LOGITS
     if
    1.86
     which
    1.77
     how
    1.70
     should
    1.41
     shouldn
    1.29
     since
    1.28
     when
    1.27
     didn
    1.24
     apparently
    1.23
     that
    1.23
    Activations Density 0.034%

    No Known Activations