© 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. 60692
    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
     our
    -1.48
     when
    -1.44
     and
    -1.41
     which
    -1.40
     where
    -1.38
    !
    -1.28
     arşivlendi
    -1.27
     Hingga
    -1.26
     this
    -1.23
    if
    -1.23
    POSITIVE LOGITS
    óta
    1.44
     univerz
    1.44
     
    1.42
     pozo
    1.38
     tazas
    1.38
    炕
    1.37
     burbujas
    1.35
     porcelana
    1.34
     aniversario
    1.30
     strukt
    1.30
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.