© 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. 227025
    Prev
    Next
    INDEX
    Explanations

    references, Inc., link, numbers

    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
    0
    0.50
     your
    0.47
    L
    0.46
    \
    0.45
    乡
    0.43
     {
    0.43
     thickness
    0.43
     cares
    0.42
     У
    0.41
    P
    0.41
    POSITIVE LOGITS
     близь
    0.64
    evším
    0.54
     شرطونو
    0.49
    𓏸
    0.49
    স্থাপ
    0.48
     Dessous
    0.48
    findById
    0.48
    ১৫
    0.48
    𒃶
    0.48
    radiative
    0.47
    Activations Density 0.001%

    No Known Activations