© 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. 29906
    Prev
    Next
    INDEX
    Explanations

    mistakes and mistranslations

    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
     RU
    -0.77
     Gracie
    -0.76
     लि
    -0.74
     MIA
    -0.73
    REAS
    -0.71
     prequel
    -0.71
    素
    -0.71
     Wr
    -0.71
    REVIEW
    -0.70
    WU
    -0.70
    POSITIVE LOGITS
    Mist
    0.94
     Mist
    0.93
     mist
    0.90
     shelters
    0.87
    mist
    0.85
     dezen
    0.77
    akes
    0.75
     Meisters
    0.75
     climático
    0.73
    本质
    0.73
    Activations Density 0.022%

    No Known Activations