© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71117
    Prev
    Next
    INDEX
    Explanations

    Starts phrases

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

    The neuron fires on tokens that begin a new line or section (i.e. the first substantive, usually capitalized, word or symbol at the start of paragraphs, headings, verse lines, or list items).

    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
     of
    -1.41
     In
    -1.26
     from
    -1.23
     different
    -1.21
     three
    -1.11
     five
    -1.10
     comes
    -1.09
     four
    -1.09
     over
    -1.08
     s
    -1.07
    POSITIVE LOGITS
    having
    1.31
     armé
    1.28
     Verordnung
    1.27
    ówki
    1.23
     remarkably
    1.23
    慙
    1.23
     REALLY
    1.22
     و
    1.22
    they
    1.19
    -​
    1.19
    Activations Density 0.008%

    No Known Activations