© 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. 31163
    Prev
    Next
    INDEX
    Explanations

    global and window objects

    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
     Carpenter
    -0.82
    Parameterized
    -0.76
     Standard
    -0.75
    int
    -0.74
    GEBURTSDATUM
    -0.72
     algebraic
    -0.71
     int
    -0.70
    chengladbach
    -0.70
    acetic
    -0.69
     Gener
    -0.69
    POSITIVE LOGITS
     window
    2.67
    window
    2.31
     windows
    1.67
    Window
    1.63
     WINDOW
    1.59
     Window
    1.55
     ventana
    1.48
    WINDOW
    1.48
     fenêtre
    1.45
    窓
    1.45
    Activations Density 0.069%

    No Known Activations