© 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. 72996
    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
     it
    -1.31
     for
    -1.31
     what
    -1.08
     with
    -1.05
     আপ
    -1.03
     since
    -1.02
    classed
    -0.99
     Gesellschaft
    -0.98
     If
    -0.98
     "+
    -0.95
    POSITIVE LOGITS
     puramente
    1.10
    avocat
    1.05
     obicei
    1.03
     Aetna
    1.02
    Colore
    1.02
     horrid
    1.02
    Bila
    1.02
     betreffende
    1.01
    Studi
    1.00
    חים
    0.98
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.