© 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. 118766
    Prev
    Next
    INDEX
    Explanations

    Last.fm, Ronin, wish

    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
     derzeit
    -1.66
     două
    -1.57
     competitivo
    -1.46
     determinadas
    -1.46
    tät
    -1.45
    <i>
    -1.43
    Its
    -1.41
    👎
    -1.41
     bislang
    -1.38
    歺
    -1.38
    POSITIVE LOGITS
     \
    1.37
     dont
    1.36
    𝖊
    1.28
     which
    1.28
     с
    1.25
    тифика
    1.24
    graphicx
    1.23
    
    1.20
    韋
    1.20
     de
    1.20
    Activations Density 0.002%

    No Known Activations