© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 816
    Prev
    Next
    INDEX
    Explanations

    closing eyes or doors

    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
    Negative Logits
     அட்ட
    0.38
     stars
    0.37
     رکن
    0.36
    Perry
    0.35
    Hob
    0.35
     Konst
    0.35
     pres
    0.35
     Outline
    0.35
    昉
    0.35
    })=
    0.35
    POSITIVE LOGITS
     закры
    1.33
     closed
    1.29
     closes
    1.15
     Closed
    1.14
    Closed
    1.12
    閉
    1.12
     zamknię
    1.09
     CLOSED
    1.07
    closed
    1.06
     chiuso
    1.02
    Activations Density 0.020%

    No Known Activations