© 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. 106430
    Prev
    Next
    INDEX
    Explanations

    XML version declarations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Packaging
    -0.73
    rzez
    -0.68
    Montana
    -0.67
    Ӧ
    -0.64
    Agency
    -0.64
    以下の
    -0.63
    قي
    -0.63
    🧗
    -0.63
    zott
    -0.63
     Mubarak
    -0.62
    POSITIVE LOGITS
    õi
    0.72
     pix
    0.70
    iga
    0.69
     Alvin
    0.68
     pars
    0.68
     şir
    0.68
     thị
    0.65
     bats
    0.65
     pintura
    0.64
     peinture
    0.64
    Activations Density 0.106%

    No Known Activations