© 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. 129056
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ઉ
    -1.21
    ત્
    -1.16
     weirdly
    -1.15
     標
    -1.15
     znamená
    -1.13
     thinks
    -1.13
    ed
    -1.12
    ésil
    -1.11
     який
    -1.11
     creates
    -1.11
    POSITIVE LOGITS
     calendrier
    1.26
    '
    1.22
     outras
    1.21
     mesmerizing
    1.14
     typelib
    1.13
    了出去
    1.13
     других
    1.13
     we
    1.12
    "
    1.12
     ситуации
    1.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.