© 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. 98526
    Prev
    Next
    INDEX
    Explanations

    app features

    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_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
    }));
    -1.00
    quial
    -0.82
     Доба
    -0.82
     hidupnya
    -0.79
    ندر
    -0.78
    šno
    -0.78
    NonQuery
    -0.77
    лії
    -0.77
    Especificación
    -0.76
    Wc
    -0.76
    POSITIVE LOGITS
     features
    4.09
     Features
    3.53
    Features
    3.52
    features
    3.31
    FEATURES
    3.00
     FEATURES
    2.84
     feature
    2.48
    Highlights
    2.28
     highlights
    2.27
     benefits
    2.16
    Activations Density 0.068%

    No Known Activations