© 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. 60256
    Prev
    Next
    INDEX
    Explanations

    references to documentation or files

    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
     where
    -1.91
     not
    -1.79
     what
    -1.75
     It
    -1.47
     can
    -1.47
     где
    -1.38
    2
    -1.34
     when
    -1.33
     donde
    -1.32
    1
    -1.32
    POSITIVE LOGITS
     tém
    1.53
    他們
    1.52
     the
    1.48
     anún
    1.47
     camiset
    1.42
    opportunities
    1.41
     pérd
    1.40
    banez
    1.40
     incrí
    1.39
    ḿ
    1.39
    Activations Density 0.217%

    No Known Activations