© 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. 25790
    Prev
    Next
    INDEX
    Explanations

    MICR font

    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
    стить
    -0.76
     premature
    -0.71
     Saxe
    -0.70
     sexual
    -0.69
     четвер
    -0.68
    alyptus
    -0.68
    ъл
    -0.67
    DAL
    -0.67
    ρού
    -0.66
    ṟ
    -0.66
    POSITIVE LOGITS
     font
    1.50
    font
    1.29
     fonts
    1.27
     monos
    1.23
    Font
    1.16
    QFont
    1.12
     Courier
    1.10
     Font
    1.10
     fixed
    1.09
    mono
    1.06
    Activations Density 0.050%

    No Known Activations