© 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. 10-GEMMASCOPE-RES-131K
    7. 45528
    Prev
    Next
    INDEX
    Explanations

    specific terms and entities

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     —
    -1.81
     Gebäude
    -1.74
    s
    -1.71
     graciosas
    -1.70
     preciosas
    -1.64
     consideradas
    -1.63
     comprometido
    -1.58
     glän
    -1.50
     sabido
    -1.50
     logrado
    -1.48
    POSITIVE LOGITS
    {
    2.20
    <bos>
    2.17
     contenido
    1.99
    ."));
    1.96
    ;
    1.95
    istungen
    1.93
     to
    1.91
    荩
    1.89
    ༴
    1.87
     muchos
    1.85
    Activations Density 0.010%

    No Known Activations