© 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. 110788
    Prev
    Next
    INDEX
    Explanations

    AntiForgeryToken

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

    the name "Foucault" or references to it.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    蕷
    -2.11
     bénévol
    -2.08
    B
    -1.98
     trésor
    -1.95
    ркут
    -1.89
    秾
    -1.82
    𐑂
    -1.81
    "/"
    -1.78
     thème
    -1.76
    她的
    -1.74
    POSITIVE LOGITS
    ?”
    2.56
     “
    2.36
     they
    2.34
    .
    2.25
    诵
    2.17
     (“
    2.02
    挥手
    1.89
    ”،
    1.86
     Undoubtedly
    1.84
     Importantly
    1.79
    Activations Density 0.000%

    No Known Activations