© 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. 75254
    Prev
    Next
    INDEX
    Explanations

    python code definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     hés
    -1.69
     célè
    -1.65
     véhic
    -1.57
     rése
    -1.53
     refroid
    -1.52
     ajedrez
    -1.52
     éve
    -1.50
    ﺇ
    -1.49
    
    -1.46
     améliorer
    -1.44
    POSITIVE LOGITS
     when
    1.71
     for
    1.48
     some
    1.46
     only
    1.45
     what
    1.45
     where
    1.42
     new
    1.42
     F
    1.40
     just
    1.36
     D
    1.34
    Activations Density 0.001%

    No Known Activations