© 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. 102742
    Prev
    Next
    INDEX
    Explanations

    up-and-coming development

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

    potential bugs and errors

    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
    Not in Any Lists

    No Comments

    Negative Logits
     comércio
    0.50
    Thirty
    0.47
     Fachwerk
    0.45
    垄
    0.43
    Anton
    0.43
    Five
    0.43
    Each
    0.43
    The
    0.42
    Cars
    0.42
    From
    0.42
    POSITIVE LOGITS
     equiv
    0.48
    ratulations
    0.44
    娥
    0.43
     gonna
    0.43
     bap
    0.41
     sweatshirts
    0.41
     យើង
    0.40
    ايبي
    0.40
    ovice
    0.40
     تضيفلها
    0.40
    Activations Density 0.001%

    No Known Activations