© 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. 106138
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    rencia
    -0.85
     all
    -0.81
    替え
    -0.81
     even
    -0.78
     one
    -0.77
    زین
    -0.77
    věr
    -0.77
     then
    -0.77
    있는
    -0.77
     Youtube
    -0.76
    POSITIVE LOGITS
    Hozzá
    0.88
    迩
    0.88
    När
    0.87
    ellä
    0.84
     説明
    0.83
    Seguir
    0.83
    ᗷ
    0.82
    Capacidad
    0.80
     anunció
    0.80
    ौर
    0.80
    Activations Density 0.027%

    No Known Activations