© 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. 98794
    Prev
    Next
    INDEX
    Explanations

    well-known

    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
     to
    -2.36
     my
    -1.83
    S
    -1.80
    other
    -1.78
     other
    -1.70
    V
    -1.70
     of
    -1.69
     但
    -1.67
    ть
    -1.64
     latter
    -1.63
    POSITIVE LOGITS
    Ꮵ
    1.85
    媜
    1.78
    蕻
    1.78
     coloridos
    1.72
     japonés
    1.72
    gebouw
    1.72
     gouttes
    1.71
     giyim
    1.71
     стоковые
    1.70
     fraî
    1.70
    Activations Density 0.013%

    No Known Activations