© 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. 31-GEMMASCOPE-2-RES-262K
    7. 129211
    Prev
    Next
    INDEX
    Explanations

    below to

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     контро
    0.45
     quarrels
    0.45
    记
    0.45
    璜
    0.45
     począ
    0.44
    ᕝ
    0.43
    AspectRatio
    0.43
    Notation
    0.42
    埄
    0.42
     polymorphisms
    0.42
    POSITIVE LOGITS
    ot
    0.58
    la
    0.57
     to
    0.57
     whose
    0.57
     on
    0.55
     that
    0.54
     Employees
    0.51
    ida
    0.50
    uri
    0.49
    ino
    0.49
    Activations Density 0.006%

    No Known Activations