© 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. 69206
    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
     only
    -1.47
    ३
    -1.29
     before
    -1.27
     lengu
    -1.19
     for
    -1.17
     है
    -1.15
     until
    -1.14
     on
    -1.14
    २
    -1.13
     epitom
    -1.12
    POSITIVE LOGITS
    Aantal
    1.32
    chaussure
    1.25
    Terug
    1.24
    Informazioni
    1.23
    Descriere
    1.22
    assage
    1.22
     douze
    1.20
    recette
    1.20
     différents
    1.20
    Ingredienti
    1.17
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.