© 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. 137766
    Prev
    Next
    INDEX
    Explanations

    users who have already shown interest

    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
     Tar
    0.45
    Tar
    0.41
     tar
    0.39
    슴
    0.38
     Medium
    0.38
     lists
    0.38
     Ashby
    0.37
     Che
    0.37
    har
    0.37
     alm
    0.37
    POSITIVE LOGITS
    পুরা
    0.40
     Wife
    0.38
     isAuthenticated
    0.38
     আবারও
    0.37
    ('$
    0.36
     আগেও
    0.35
     తెర
    0.35
     رابط
    0.34
     জন্
    0.34
     жена
    0.34
    Activations Density 0.000%

    No Known Activations