© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60765
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Föld
    -1.34
    %;
    
    -1.23
    czę
    -1.20
    Ї
    -1.18
     if
    -1.16
     présidentielle
    -1.16
    長の
    -1.13
    torie
    -1.13
     gitti
    -1.13
     éter
    -1.11
    POSITIVE LOGITS
    public
    1.43
     weihnachten
    1.33
    や
    1.30
    なので
    1.23
    Interes
    1.20
     dee
    1.16
    ちなみに
    1.16
     albero
    1.14
     erwäh
    1.14
     exceedingly
    1.14
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.