© 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. 15153
    Prev
    Next
    INDEX
    Explanations

    Xamarin Forms code

    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
    bawa
    -1.18
    badan
    -1.18
     після
    -1.13
    QtWidgets
    -1.12
     wort
    -1.12
     merupakan
    -1.11
     EXACT
    -1.11
    bantu
    -1.10
     első
    -1.09
    亠
    -1.09
    POSITIVE LOGITS
     even
    1.27
     where
    1.21
     и
    1.20
     >
    1.13
     посмотреть
    1.13
     just
    1.12
     possibly
    1.12
     février
    1.11
     it
    1.09
     perhaps
    1.09
    Activations Density 0.082%

    No Known Activations