© 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. 200227
    Prev
    Next
    INDEX
    Explanations

    machine learning models

    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
     réussite
    0.49
    渽
    0.49
    ინი
    0.45
     повідом
    0.45
     упраж
    0.45
     Theorie
    0.44
     levelled
    0.44
    Hallo
    0.43
     parfaite
    0.43
     PLIST
    0.43
    POSITIVE LOGITS
     or
    0.68
    max
    0.61
    f
    0.59
    )+
    0.59
    shape
    0.59
    或
    0.58
    size
    0.57
    or
    0.57
    res
    0.57
    axis
    0.56
    Activations Density 0.006%

    No Known Activations