© 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. 124710
    Prev
    Next
    INDEX
    Explanations

    literary titles and authors

    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
     AppColors
    -1.27
     THOM
    -1.23
    kiksi
    -1.21
    ﹍﹍
    -1.18
     شنبه
    -1.17
    ícia
    -1.16
     kvinder
    -1.15
     ErrInvalid
    -1.14
    ()",
    -1.13
     uruguay
    -1.11
    POSITIVE LOGITS
    でしたか
    1.29
     olsa
    1.22
     don
    1.15
     viaj
    1.14
    有多少
    1.13
    aughey
    1.13
    льність
    1.12
    ilität
    1.12
     at
    1.11
     çalışma
    1.09
    Activations Density 0.012%

    No Known Activations