© 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. 68136
    Prev
    Next
    INDEX
    Explanations

    decided to / know the

    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
    Ри
    0.52
    ש
    0.50
    Merge
    0.47
    боро
    0.47
    нинг
    0.45
     કર્યું
    0.45
    Logout
    0.45
    ো
    0.45
    ('{
    0.45
    Logging
    0.44
    POSITIVE LOGITS
     Bick
    0.50
     그려
    0.49
     Traditionally
    0.44
     Ruth
    0.43
    rooted
    0.43
     thereafter
    0.43
     मैदा
    0.43
    ).
    0.42
     lekar
    0.42
     brother
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.