© 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. 2027
    Prev
    Next
    INDEX
    Explanations

    right click and double click

    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
    агностика
    -0.80
    swig
    -0.77
    באנגלית
    -0.75
     سوز
    -0.73
    Vikt
    -0.71
     CONSIDER
    -0.70
    Waktu
    -0.70
     syringes
    -0.69
    ※※
    -0.69
    unggah
    -0.68
    POSITIVE LOGITS
     click
    2.69
    click
    2.42
    Click
    2.23
     clicking
    2.05
     Click
    2.00
     clicks
    1.75
    CLICK
    1.69
    クリック
    1.67
     clicked
    1.62
    clicking
    1.55
    Activations Density 0.033%

    No Known Activations