© 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. 2938
    Prev
    Next
    INDEX
    Explanations

    Explaining or defining concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    sentences that introduce or define a concept (definition/introductory phrases like "X is/are ..." or "X: Explained").

    oai_token-act-pair · gpt-5-mini
    Triggered by @yooniel31
    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
    这是
    0.37
    这是一个
    0.36
    这也是
    0.35
    ایات
    0.32
    来说
    0.32
    各个
    0.31
    也不会
    0.31
    এর
    0.31
     اینجا
    0.31
    失败
    0.31
    POSITIVE LOGITS
    that
    0.51
     that
    0.50
     whose
    0.48
     whereby
    0.45
     რომელიც
    0.44
     kwamba
    0.43
     cuya
    0.42
     που
    0.41
    タイプの
    0.41
     designed
    0.40
    Activations Density 0.245%

    No Known Activations