© 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. 63090
    Prev
    Next
    INDEX
    Explanations

    percentage values

    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
    ਿਆ
    -0.84
    nearly
    -0.81
     σχε
    -0.78
    lesias
    -0.77
     av
    -0.77
    rtner
    -0.75
    õi
    -0.74
     SHORT
    -0.72
     almost
    -0.71
     nearly
    -0.71
    POSITIVE LOGITS
    百分之
    2.05
     percent
    1.97
     %
    1.97
    %
    1.92
     percentage
    1.86
     Percent
    1.69
     \%
    1.63
    percent
    1.62
     percentages
    1.59
    Percent
    1.59
    Activations Density 0.075%

    No Known Activations