© 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. 128847
    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
     for
    -1.44
     who
    -1.40
     to
    -1.27
     this
    -1.19
     bazar
    -1.13
    !(:
    -1.08
     vnder
    -1.05
     Diarsipkan
    -1.03
    chaise
    -1.02
    сети
    -1.01
    POSITIVE LOGITS
    excellents
    1.07
    </tr>
    1.01
     cuales
    0.97
    asks
    0.97
     nez
    0.96
    的两
    0.96
     złota
    0.96
    indest
    0.96
    Evet
    0.95
     serce
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.