© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127837
    Prev
    Next
    INDEX
    Explanations

    code questions and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     教程
    -1.30
     手绘
    -1.20
     kolye
    -1.16
     }(\
    -1.15
     veckan
    -1.14
     morgon
    -1.10
     dårlig
    -1.10
     tillegg
    -1.10
    岁的
    -1.07
    Ꮏ
    -1.07
    POSITIVE LOGITS
    うえ
    0.99
     wybór
    0.94
    ).
    0.93
     négociations
    0.90
     остров
    0.88
     lì
    0.88
    .*;
    0.88
    ようになって
    0.88
    rounded
    0.87
    ところは
    0.87
    Activations Density 0.000%

    No Known Activations