© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65022
    Prev
    Next
    INDEX
    Explanations

    tar archives and files

    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
     zip
    -1.16
     Zip
    -1.11
    Zip
    -1.02
    ZIP
    -1.00
    zip
    -0.94
     ZIP
    -0.93
     zipper
    -0.93
    unzip
    -0.91
    Zi
    -0.90
     zippers
    -0.88
    POSITIVE LOGITS
    xf
    0.83
    Tar
    0.82
    ball
    0.80
    tar
    0.79
     archive
    0.77
    ล่า
    0.76
     tar
    0.75
    BALL
    0.75
    TAR
    0.74
     solar
    0.73
    Activations Density 0.024%

    No Known Activations