© 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. 32814
    Prev
    Next
    INDEX
    Explanations

    numbers and specific instances

    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
     основные
    -1.06
     старый
    -1.05
     недостатки
    -1.02
     parezca
    -1.02
    ênio
    -1.02
    ække
    -0.98
     nung
    -0.98
     Bacteriol
    -0.98
    饜
    -0.97
     новое
    -0.96
    POSITIVE LOGITS
    是怎么回事
    1.07
    businessman
    1.02
    ERICAN
    0.97
     misconceptions
    0.96
     two
    0.94
     TAMBIÉN
    0.92
    については
    0.90
    Also
    0.88
    komendasi
    0.87
     constructive
    0.86
    Activations Density 0.010%

    No Known Activations