© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130899
    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
     our
    -1.55
     two
    -1.45
     what
    -1.43
     first
    -1.34
     with
    -1.33
     both
    -1.30
     when
    -1.27
     three
    -1.27
     where
    -1.27
     some
    -1.26
    POSITIVE LOGITS
     publier
    1.37
     royaume
    1.36
    釓
    1.29
     ouvrir
    1.25
    Terug
    1.23
     {
    1.22
     만화
    1.21
     caduta
    1.20
    Oby
    1.20
     célè
    1.20
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.