© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128113
    Prev
    Next
    INDEX
    Explanations

    more information or details

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

    The neuron fires on editorial or moderator‐style prompts asking the user to provide more information, clarification, or to post configuration/details.

    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
     ujar
    -1.40
    着一
    -1.38
     alue
    -1.36
     rú
    -1.35
     parlamentar
    -1.27
     onlyOwner
    -1.26
     parfüm
    -1.24
    ⠀
    -1.23
     发表于
    -1.22
     atrás
    -1.21
    POSITIVE LOGITS
     that
    2.06
     which
    1.80
     how
    1.73
     if
    1.73
     more
    1.70
     it
    1.66
     its
    1.55
     whether
    1.55
     since
    1.48
     or
    1.48
    Activations Density 0.064%

    No Known Activations