© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101728
    Prev
    Next
    INDEX
    Explanations

    window and related structures

    np_acts-logits-general · gemini-2.5-flash-lite

    window and balcony

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    0.53
    u
    0.46
    users
    0.44
    ₡
    0.43
    ק
    0.42
    eleration
    0.42
    𝕥
    0.41
    chandelier
    0.41
    عة
    0.41
     crystal
    0.40
    POSITIVE LOGITS
     ventana
    0.72
     janela
    0.71
     fenêtre
    0.68
     Window
    0.67
     ventanas
    0.67
     window
    0.66
     jendela
    0.62
    WINDOW
    0.60
    窗
    0.60
     finestra
    0.59
    Activations Density 0.065%

    No Known Activations