© 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. 22-GEMMASCOPE-RES-131K
    7. 34474
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and variables

    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_22/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
    imwrite
    -1.07
     fourth
    -1.03
    șe
    -1.02
     some
    -1.02
     giày
    -1.01
    libft
    -0.99
     Acest
    -0.99
     north
    -0.99
     Estamos
    -0.99
     Gebruik
    -0.98
    POSITIVE LOGITS
    that
    1.01
    Item
    0.91
    item
    0.88
    do
    0.88
    ci
    0.86
    ti
    0.85
    each
    0.84
    手に入
    0.84
    Автор
    0.84
    ()
    0.84
    Activations Density 0.015%

    No Known Activations