© 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. 47097
    Prev
    Next
    INDEX
    Explanations

    questions and introductions

    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
    GameMode
    -0.84
     sucede
    -0.81
    ünk
    -0.79
    ۔
    -0.79
     ۔
    -0.77
    واف
    -0.76
     different
    -0.76
    PTI
    -0.75
     denk
    -0.72
    practical
    -0.71
    POSITIVE LOGITS
    ⌕
    0.92
    噘
    0.82
     Telugu
    0.81
     TSV
    0.81
     lessee
    0.81
    uanto
    0.81
     Bhar
    0.80
     relics
    0.79
    velser
    0.78
     anuncios
    0.78
    Activations Density 0.003%

    No Known Activations