© 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. 34-GEMMASCOPE-RES-131K
    7. 89833
    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
     Mischung
    -1.03
     dní
    -0.85
    %;
    -0.82
    timedelta
    -0.82
    ਘ
    -0.82
    Several
    -0.81
    ücksich
    -0.81
    ｷ
    -0.80
    ztály
    -0.78
    minify
    -0.78
    POSITIVE LOGITS
     общий
    0.90
    leb
    0.89
     corrientes
    0.87
    𝓇
    0.86
    评分
    0.84
    HELP
    0.84
     überprüft
    0.81
     derselben
    0.81
     serdecznie
    0.78
    kö
    0.77
    Activations Density 0.000%

    No Known Activations