© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2778
    Prev
    Next
    INDEX
    Explanations

    line and column references

    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
    pages
    -1.09
    Pages
    -0.81
     APPLE
    -0.77
     Brawl
    -0.76
     ваших
    -0.73
    Интере
    -0.72
     ORG
    -0.72
    APPLE
    -0.71
     pages
    -0.71
     Pages
    -0.71
    POSITIVE LOGITS
     lines
    1.83
     line
    1.43
     Lines
    1.36
    lines
    1.23
    Lines
    1.20
     Line
    1.19
     middle
    1.13
     last
    1.11
     bottom
    1.10
    line
    1.09
    Activations Density 0.022%

    No Known Activations