© 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. 73790
    Prev
    Next
    INDEX
    Explanations

    section headings

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    鴆
    -2.53
    "
    -2.48
    the
    -2.47
    }$
    -2.33
    p
    -2.31
    d
    -2.25
    a
    -2.22
    なぁ
    -2.08
    ور
    -2.02
     quaisquer
    -1.99
    POSITIVE LOGITS
    ࿙
    3.44
    ╿
    2.80
    遢
    2.73
    ﯼ
    2.72
    ଢ
    2.56
    ：“
    2.53
    睒
    2.44
    tủ
    2.39
    ٳ
    2.30
    ↵
    2.28
    Activations Density 0.001%

    No Known Activations