© 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. 16665
    Prev
    Next
    INDEX
    Explanations

    events and their consequences

    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
    también
    -0.90
    ッド
    -0.88
     estoy
    -0.81
     you
    -0.79
     فقد
    -0.77
    liš
    -0.77
    बा
    -0.75
     llam
    -0.75
     appeal
    -0.75
     лин
    -0.74
    POSITIVE LOGITS
     결과
    1.43
     resulting
    1.41
     result
    1.29
     resulted
    1.26
     Result
    1.21
    Result
    1.16
     resultant
    1.16
    结果
    1.14
    結果
    1.11
    resulting
    1.10
    Activations Density 0.090%

    No Known Activations