© 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. 8979
    Prev
    Next
    INDEX
    Explanations

    listing items with qualifiers

    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
    *);
    -1.33
    oluble
    -1.24
     version
    -1.23
    ométrique
    -1.23
     Delhi
    -1.23
    vají
    -1.22
    理石
    -1.22
     .\
    -1.22
     concept
    -1.20
    &
    -1.19
    POSITIVE LOGITS
     appunt
    1.64
     our
    1.55
     soste
    1.39
     salita
    1.36
     pietre
    1.34
     merce
    1.34
     specchio
    1.34
     commerci
    1.34
     Secrétaire
    1.33
     sappi
    1.32
    Activations Density 0.034%

    No Known Activations