© 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. 24667
    Prev
    Next
    INDEX
    Explanations

    Ms

    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
    -
    0.45
     S
    0.44
     K
    0.42
    speople
    0.42
    osomes
    0.41
    Sliders
    0.41
    шими
    0.41
     I
    0.40
     Lot
    0.40
     Για
    0.38
    POSITIVE LOGITS
    ь
    0.50
    లు
    0.47
    们
    0.47
    و
    0.46
     niej
    0.45
    اج
    0.45
    ین
    0.45
     facebook
    0.44
    ف
    0.44
    കള്‍
    0.44
    Activations Density 0.009%

    No Known Activations