© 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. 92541
    Prev
    Next
    INDEX
    Explanations

    colored covers

    np_acts-logits-general · gemini-2.5-flash-lite

    items and requirements

    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
    D
    0.49
    getNext
    0.49
    T
    0.46
    gent
    0.46
    ^{-}$
    0.44
    traverse
    0.44
    gunta
    0.44
     غیر
    0.43
    typically
    0.42
    r
    0.41
    POSITIVE LOGITS
    zuge
    0.47
    enie
    0.47
     বস
    0.46
     государственной
    0.46
     времен
    0.45
    ārt
    0.44
     renverse
    0.44
     vorge
    0.44
    acles
    0.43
     lovingly
    0.43
    Activations Density 0.001%

    No Known Activations