© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 101289
    Prev
    Next
    INDEX
    Explanations

    pane or panes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Door
    0.55
     door
    0.50
     Door
    0.49
    ドア
    0.48
    door
    0.45
     DOOR
    0.42
    门
    0.40
    卟
    0.40
     Vault
    0.40
    Vault
    0.40
    POSITIVE LOGITS
     pane
    1.55
     Pane
    1.46
    pane
    1.39
    Pane
    1.38
     panes
    1.34
     windowsill
    0.92
     sill
    0.76
     glass
    0.73
     Pani
    0.70
     pan
    0.68
    Activations Density 0.001%

    No Known Activations