© 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. 167686
    Prev
    Next
    INDEX
    Explanations

    law, science, and biography

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

    explanation of components or issues

    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
    Negative Logits
    の人
    0.50
    博物
    0.50
     broj
    0.48
    ファイ
    0.47
    ヨーロッパ
    0.46
    された
    0.46
    ジョン
    0.45
     ontv
    0.45
    悵
    0.45
    ジュニア
    0.44
    POSITIVE LOGITS
     圆
    0.50
    ↵
    0.50
    ins
    0.48
    chemistry
    0.48
     Biochemistry
    0.48
     build
    0.46
    ్ఞ
    0.46
     error
    0.46
    limit
    0.46
     EX
    0.46
    Activations Density 0.000%

    No Known Activations