© 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. 135415
    Prev
    Next
    INDEX
    Explanations

    changes and variety

    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
    Not in Any Lists

    No Comments

    Negative Logits
     придума
    0.47
    ʷ
    0.45
    解决
    0.45
     కోసం
    0.45
    优雅
    0.44
    健
    0.44
    乐观
    0.43
     raconte
    0.42
     때
    0.41
     εύ
    0.41
    POSITIVE LOGITS
     ebenfalls
    0.54
     kasnije
    0.49
     kobiet
    0.47
     militares
    0.46
     jalan
    0.46
     turkeys
    0.46
    뵌
    0.46
     innych
    0.45
     cambia
    0.44
     drugih
    0.44
    Activations Density 0.018%

    No Known Activations