© 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. 39826
    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
    r
    -1.88
     their
    -1.47
     bolster
    -1.45
     Jedes
    -1.43
     burgeoning
    -1.42
     furthering
    -1.35
    (
    -1.31
     vehemently
    -1.30
    ,
    -1.30
     Möglich
    -1.30
    POSITIVE LOGITS
    这也是
    2.03
    ୱ
    1.88
     is
    1.76
    could
    1.66
     Fotografía
    1.66
     será
    1.65
    ilogue
    1.65
     queste
    1.64
    就可以
    1.63
    はこの
    1.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.