© 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. 24884
    Prev
    Next
    INDEX
    Explanations

    background color professional broken

    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
    AKER
    0.37
    εν
    0.35
    ेंज
    0.35
     പഞ്ച
    0.35
     আইন
    0.34
     relazione
    0.34
    τού
    0.34
    差し
    0.34
    moor
    0.33
    Ռ
    0.33
    POSITIVE LOGITS
    깆
    0.41
     prévoit
    0.40
     ఒకటి
    0.40
     vä
    0.39
     egalitarian
    0.39
     Juz
    0.38
    പ്
    0.38
     vessels
    0.37
     Susan
    0.37
     బాగా
    0.37
    Activations Density 0.000%

    No Known Activations