© 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. 66009
    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
     all
    -1.49
     from
    -1.48
     by
    -1.41
     its
    -1.20
     themselves
    -1.18
     on
    -1.17
     капю
    -1.16
     аро
    -1.13
     or
    -1.13
     found
    -1.08
    POSITIVE LOGITS
     těchto
    1.33
    
    1.20
     cliquant
    1.19
     câmbio
    1.16
     protože
    1.14
     ausgesprochen
    1.13
    (>
    1.13
    .>
    1.12
     shu
    1.11
     there
    1.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.