© 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. 124767
    Prev
    Next
    INDEX
    Explanations

    under the Apache License

    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
     even
    -1.80
     on
    -1.78
     in
    -1.63
     all
    -1.55
     have
    -1.40
     bahkan
    -1.37
     more
    -1.30
     like
    -1.29
     because
    -1.29
     their
    -1.27
    POSITIVE LOGITS
     '['
    1.62
     '-':
    1.54
     '\''
    1.49
     осуществляется
    1.49
     '-';
    1.48
     которой
    1.48
    ésor
    1.47
    Its
    1.44
    Always
    1.43
     laquelle
    1.43
    Activations Density 0.038%

    No Known Activations