© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101006
    Prev
    Next
    INDEX
    Explanations

    unitary transformations and groups

    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
    呟
    -1.48
    特に
    -1.46
    一说
    -1.41
    礎
    -1.38
    unes
    -1.35
    不上
    -1.34
     desses
    -1.34
     décisions
    -1.33
    être
    -1.31
     especialmente
    -1.31
    POSITIVE LOGITS
     as
    1.57
    gemeins
    1.30
     within
    1.28
     malattie
    1.19
    4
    1.18
     Following
    1.17
    ”-
    1.17
     rámci
    1.17
     innebär
    1.16
    :"-
    1.14
    Activations Density 0.041%

    No Known Activations