© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74939
    Prev
    Next
    INDEX
    Explanations

    questions and descriptive words

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

    The neuron is triggered by soft‐hyphen characters (the “­” hyphenation markers used when words are split across lines).

    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
    。"
    -2.30
     unwavering
    -2.14
    ！！！！
    -2.09
    Donativos
    -2.09
     when
    -2.09
    ဴ
    -2.00
    "+
    -1.98
     =
    -1.98
    棐
    -1.98
     intricate
    -1.94
    POSITIVE LOGITS
     decidedly
    2.55
     famed
    2.44
    [
    2.36
     renowned
    2.36
    –
    2.34
    蟥
    2.30
    峮
    2.28
     delightfully
    2.25
     remarkably
    2.22
    ’
    2.19
    Activations Density 0.008%

    No Known Activations