© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 226749
    Prev
    Next
    INDEX
    Explanations

    complete series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     elves
    0.51
    𝑒
    0.50
     Gram
    0.49
    inoff
    0.48
     dinast
    0.48
     dne
    0.47
     tigers
    0.45
     제대로
    0.45
    Gram
    0.45
     Blogs
    0.44
    POSITIVE LOGITS
    u
    0.48
     FRAME
    0.47
    ATURE
    0.45
    PLACE
    0.44
     diversification
    0.44
    FRAME
    0.44
    PLATE
    0.43
    BRID
    0.43
     variété
    0.42
    ométrique
    0.42
    Activations Density 0.000%

    No Known Activations