© 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. 22-GEMMASCOPE-RES-131K
    7. 15809
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     their
    -1.55
     [
    -1.30
     your
    -1.28
    或
    -1.27
     岡
    -1.14
     have
    -1.12
     there
    -1.08
     \
    -1.08
     does
    -1.07
     are
    -1.06
    POSITIVE LOGITS
    itzende
    1.26
    jspx
    1.22
    onViewCreated
    1.19
     宝宝
    1.19
     οποία
    1.16
    Estar
    1.13
    ౫
    1.12
    trail
    1.11
     поэтому
    1.11
    tą
    1.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.