© 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. 10-GEMMASCOPE-RES-131K
    7. 60930
    Prev
    Next
    INDEX
    Explanations

    often followed by diverse descriptions

    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_10/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
    </i>
    -2.14
    \
    -1.80
    /
    -1.78
    this
    -1.75
     &
    -1.66
    :
    -1.63
     are
    -1.59
    4
    -1.54
    ni
    -1.53
    N
    -1.53
    POSITIVE LOGITS
     sogar
    2.16
    dáms
    1.74
     velmi
    1.73
    
    1.72
    pochette
    1.65
    mpagne
    1.63
     atracciones
    1.60
    
    1.59
    纮
    1.59
     comerciantes
    1.58
    Activations Density 0.031%

    No Known Activations