© 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. 33040
    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
    áneos
    -1.31
    (
    -1.30
     in
    -1.30
    Boolean
    -1.23
    mination
    -1.23
     Aktiv
    -1.22
     دچار
    -1.20
    簓
    -1.20
     militer
    -1.19
     ефек
    -1.18
    POSITIVE LOGITS
     and
    2.05
    Governing
    1.38
    Siddhartha
    1.29
    Tornado
    1.24
    leggio
    1.23
     emisiones
    1.22
     ganancias
    1.21
     regalías
    1.21
    Monument
    1.18
    Quora
    1.18
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.