© 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. 107995
    Prev
    Next
    INDEX
    Explanations

    map of

    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
     giriş
    -0.85
    Fury
    -0.80
     mercancías
    -0.79
     HttpNotFound
    -0.79
    itars
    -0.79
     großartige
    -0.78
     unglaub
    -0.77
    ఘ
    -0.76
     Plätze
    -0.76
     ambientales
    -0.75
    POSITIVE LOGITS
     of
    1.41
     showing
    1.01
    showing
    0.94
     SHOWING
    0.94
    Showing
    0.89
    豪
    0.85
    λικά
    0.84
    пин
    0.84
    tego
    0.83
     orang
    0.83
    Activations Density 0.019%

    No Known Activations