© 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. 25369
    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
     (
    -1.21
     And
    -1.03
    nos
    -1.03
    )="
    -1.00
     we
    -1.00
    躋
    -0.95
     Assn
    -0.94
     so
    -0.94
     I
    -0.94
     if
    -0.94
    POSITIVE LOGITS
    bilde
    1.16
    bilden
    1.13
    先日
    1.13
    lindungi
    1.12
     AGRE
    1.10
    UpdateData
    1.09
     deseas
    1.07
     последнее
    1.07
    Nguy
    1.06
    plakat
    1.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.