© 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. 192009
    Prev
    Next
    INDEX
    Explanations

    their concentrations

    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
     paraît
    0.40
    gradation
    0.39
    表記
    0.38
    낚
    0.37
     लास्ट
    0.36
    eating
    0.36
     najbli
    0.36
     tale
    0.35
    owering
    0.35
    нят
    0.35
    POSITIVE LOGITS
    籀
    0.42
     Minkowski
    0.41
     schen
    0.40
     biopsy
    0.39
     bial
    0.39
    ruch
    0.38
    മ്മ
    0.37
    ayaan
    0.37
    ު
    0.37
     شیخ
    0.37
    Activations Density 0.000%

    No Known Activations