© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9149
    Prev
    Next
    INDEX
    Explanations

    closed, shut, sealed

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

    closing or shut down states

    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_40_width_16k_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
    摷
    0.39
    剐
    0.37
    arnia
    0.37
    ্ণ
    0.37
    outputPath
    0.36
     loosening
    0.35
    觐
    0.35
     clipping
    0.35
    觕
    0.35
     Dillon
    0.34
    POSITIVE LOGITS
     закры
    3.34
     closed
    3.16
    闭
    3.08
     closure
    3.06
     closes
    3.05
     closing
    3.03
    閉
    3.02
     Closed
    3.00
     zamknię
    2.95
     Closing
    2.94
    Activations Density 0.459%

    No Known Activations