© 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. 26192
    Prev
    Next
    INDEX
    Explanations

    local neighborhood

    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
     Güzel
    0.48
    .*
    0.41
     цер
    0.41
    simp
    0.41
    rah
    0.40
     ት
    0.40
     κου
    0.40
    ANTES
    0.39
    ুয়ার
    0.38
     παν
    0.38
    POSITIVE LOGITS
     avsl
    0.40
    Douglas
    0.38
    lay
    0.36
    眽
    0.35
     Douglas
    0.34
     humain
    0.34
    asarray
    0.34
     perish
    0.34
    FAX
    0.34
    chain
    0.34
    Activations Density 0.000%

    No Known Activations