© 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. 2936
    Prev
    Next
    INDEX
    Explanations

    def __init__

    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
    Merr
    0.45
    Precision
    0.44
    ars
    0.42
    Investment
    0.41
    DEM
    0.41
    Sie
    0.40
    very
    0.39
     przysz
    0.39
    Exp
    0.38
    ๐
    0.38
    POSITIVE LOGITS
     __
    0.95
    __
    0.66
    -__
    0.62
     __________
    0.61
     ____
    0.61
     ___
    0.58
     ________
    0.57
     ____________
    0.57
     _______
    0.56
     ______
    0.54
    Activations Density 0.008%

    No Known Activations