© 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. 192549
    Prev
    Next
    INDEX
    Explanations

    mother, days, book, toss, casing, colored

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

    especially when

    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
    ai
    0.51
    an
    0.45
    ben
    0.42
    eur
    0.42
    rim
    0.41
     HAZ
    0.41
    _{
    0.40
    ư
    0.40
    ut
    0.40
    dat
    0.40
    POSITIVE LOGITS
     uniquement
    0.51
    喡
    0.51
    <unused2012>
    0.51
     mín
    0.50
     possibilité
    0.49
     écrire
    0.49
     прошед
    0.48
     entièrement
    0.48
     écrit
    0.48
     toujours
    0.48
    Activations Density 0.001%

    No Known Activations