© 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. 10-GEMMASCOPE-RES-131K
    7. 66445
    Prev
    Next
    INDEX
    Explanations

    sentence-ending punctuation

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

    The neuron fires on exclamation points and similarly emphatic punctuation, flagging highly enthusiastic or exclamatory expressions.

    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
     of
    -1.84
     which
    -1.71
     on
    -1.69
     einzelnen
    -1.63
     Pokud
    -1.54
     poszczegól
    -1.48
    обзор
    -1.46
    ちゃった
    -1.45
     from
    -1.45
     Drž
    -1.44
    POSITIVE LOGITS
     любые
    1.49
     twofold
    1.47
     albeit
    1.39
     gimnas
    1.39
     любое
    1.38
     недостатки
    1.37
     bezw
    1.36
    >
    1.33
     ф
    1.30
    ">
    1.30
    Activations Density 0.023%

    No Known Activations