© 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. 21811
    Prev
    Next
    INDEX
    Explanations

    categories or types

    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
     norm
    0.45
     begins
    0.44
     setup
    0.44
     struggles
    0.43
     strategy
    0.43
     struggling
    0.42
     seeded
    0.42
     framework
    0.42
    c
    0.42
     seeding
    0.41
    POSITIVE LOGITS
    情報
    0.54
    мену
    0.47
    μμ
    0.47
    ಹೆ
    0.46
    այի
    0.45
    開店
    0.44
    訕
    0.44
    エネルギー
    0.44
     грошы
    0.43
    την
    0.43
    Activations Density 0.001%

    No Known Activations