© 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. 100073
    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
     pastillas
    -1.20
     sudor
    -1.16
     ajustable
    -1.15
     vitamine
    -1.15
     aſ
    -1.14
     morta
    -1.11
     Veneto
    -1.11
     plati
    -1.10
     élite
    -1.10
    Preparazione
    -1.10
    POSITIVE LOGITS
     L
    1.20
    ,
    1.17
     focusing
    1.13
     sehr
    1.12
     distinct
    1.09
     S
    1.08
     one
    1.07
     determine
    1.03
     A
    1.01
     serves
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.