© 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. 67821
    Prev
    Next
    INDEX
    Explanations

    brother whom, idea of, regions without

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

    describing phased implementation steps

    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
     காட்சிகள்
    0.53
    ን
    0.53
    シーン
    0.50
     ሜ
    0.49
    Ꮯ
    0.48
    ਹ
    0.47
     ד
    0.47
     ഈ
    0.46
    ネ
    0.46
     וי
    0.46
    POSITIVE LOGITS
    aggregated
    0.47
    groupBy
    0.46
    the
    0.46
    framework
    0.46
    through
    0.45
    agency
    0.44
    from
    0.44
    because
    0.44
    holder
    0.43
     because
    0.43
    Activations Density 0.001%

    No Known Activations