© 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. 34-GEMMASCOPE-RES-131K
    7. 56787
    Prev
    Next
    INDEX
    Explanations

    control flow keywords

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     especially
    -0.90
    particular
    -0.89
     terutama
    -0.89
     principally
    -0.85
     particularly
    -0.83
     aking
    -0.82
     particolare
    -0.82
     Especially
    -0.79
     PARTICULAR
    -0.78
    OnItem
    -0.77
    POSITIVE LOGITS
    ʇ
    0.77
    評
    0.76
    有的
    0.75
    Ÿ
    0.75
    доб
    0.75
    满脸
    0.74
     lugar
    0.74
    ressee
    0.73
     one
    0.72
     Garrison
    0.71
    Activations Density 0.016%

    No Known Activations