© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2341
    Prev
    Next
    INDEX
    Explanations

    listing items with bullets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ]，
    0.38
     caries
    0.34
     intelig
    0.34
     annuities
    0.33
     manipulations
    0.33
     radiographs
    0.32
     analogues
    0.32
     rearrangements
    0.32
     operands
    0.32
     patina
    0.31
    POSITIVE LOGITS
    <ul>
    0.49
    1
    0.47
    0.43
     Firstly
    0.42
    <li>
    0.42
    if
    0.42
    0.42
     A
    0.41
    一方面
    0.41
    *
    0.41
    Activations Density 1.860%

    No Known Activations