© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130472
    Prev
    Next
    INDEX
    Explanations

    but that's not

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

    This neuron fires on the deferral transition “but that’s for another article,” marking a parenthetical digression.

    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
    法國
    -1.33
     of
    -1.32
     verdaderas
    -1.30
     ACTUALLY
    -1.28
     skut
    -1.27
    TRANSLATE
    -1.26
     viejas
    -1.26
    erjee
    -1.25
    isbury
    -1.23
     mucosa
    -1.23
    POSITIVE LOGITS
    uuuuu
    1.34
    🇺🇸
    1.34
    '';
    1.34
    cased
    1.33
    urg
    1.25
    ☮
    1.25
    oh
    1.23
    ssssssss
    1.23
    zzzz
    1.22
    *~
    1.21
    Activations Density 0.035%

    No Known Activations