© 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. 104549
    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
     ayudó
    -1.16
     injurious
    -1.11
     következő
    -1.11
     Política
    -1.10
    UMS
    -1.07
    melde
    -1.07
    ליך
    -1.06
     $"{
    -1.06
    SME
    -1.04
     prachtige
    -1.03
    POSITIVE LOGITS
     when
    1.24
     that
    1.15
     which
    1.06
     If
    1.03
     then
    0.96
     actually
    0.96
     where
    0.93
     These
    0.93
     or
    0.92
     When
    0.92
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.