© 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. 78803
    Prev
    Next
    INDEX
    Explanations

    figure / figma / figment

    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
    י
    -0.85
    Equity
    -0.82
    巣
    -0.77
    çam
    -0.77
    Investigation
    -0.76
    adag
    -0.76
     zigzag
    -0.75
    ologische
    -0.74
     longitudinally
    -0.74
     autour
    -0.73
    POSITIVE LOGITS
     fig
    1.04
    figcaption
    0.92
     figure
    0.84
    fig
    0.83
    Figure
    0.80
    FIG
    0.80
    нению
    0.77
     fign
    0.75
    CLOSED
    0.75
     фигу
    0.75
    Activations Density 0.011%

    No Known Activations