© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127254
    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
    !
    -1.66
    \
    -1.55
    —
    -1.48
     Another
    -1.41
    h
    -1.34
    2
    -1.30
    --
    -1.27
    :
    -1.26
     muchísimo
    -1.24
     It
    -1.23
    POSITIVE LOGITS
     desafíos
    1.47
     rompecabezas
    1.41
     "}
    1.31
    sP
    1.30
    鹋
    1.29
    čení
    1.28
     okazji
    1.22
     alojamientos
    1.22
     tne
    1.22
     myös
    1.21
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.