© 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. 22-GEMMASCOPE-RES-131K
    4. 130834
    Prev
    Next
    INDEX
    Explanations

    configuration keys and values

    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
     parfü
    -1.84
     siè
    -1.67
     rése
    -1.63
     trône
    -1.56
     célè
    -1.55
     régiment
    -1.55
     pittores
    -1.54
    
    -1.53
     plafon
    -1.52
     atlet
    -1.52
    POSITIVE LOGITS
    D
    1.60
    C
    1.59
    S
    1.56
    F
    1.55
    L
    1.55
    J
    1.49
    A
    1.48
    Y
    1.48
     left
    1.48
    B
    1.47
    Activations Density 0.042%

    No Known Activations