© 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. 25805
    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
     their
    -1.54
     how
    -1.40
     OSError
    -1.30
     more
    -1.27
     yoksa
    -1.27
     начин
    -1.23
     wcześniej
    -1.19
     передний
    -1.16
    franco
    -1.16
     CURLOPT
    -1.16
    POSITIVE LOGITS
    Etape
    1.43
    Descriere
    1.43
    Traduction
    1.40
    Елена
    1.37
     Эти
    1.33
    KJV
    1.32
    Première
    1.30
    Escrito
    1.30
    Torna
    1.30
    Chapitre
    1.28
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.