© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 118975
    Prev
    Next
    INDEX
    Explanations

    door closing and shut

    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/layer_40_width_262k_l0_medium
    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
     doors
    0.82
     gates
    0.80
     doorways
    0.78
    Gates
    0.77
    门
    0.75
     Gates
    0.74
     cửa
    0.74
     puertas
    0.71
     Doors
    0.71
    Doors
    0.70
    POSITIVE LOGITS
     closing
    0.83
    Closing
    0.79
     Closing
    0.79
     closes
    0.72
     hinges
    0.71
     closed
    0.70
     закры
    0.68
     hinge
    0.67
    closing
    0.66
    閉
    0.66
    Activations Density 0.021%

    No Known Activations