© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84931
    Prev
    Next
    INDEX
    Explanations

    ending quote or code block

    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
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -1.66
     our
    -1.50
    liziert
    -1.48
     anderen
    -1.33
     brilh
    -1.31
    recurring
    -1.30
    それに
    -1.28
     verur
    -1.27
     דבר
    -1.27
     otros
    -1.27
    POSITIVE LOGITS
    .
    1.28
     of
    1.28
    puede
    1.27
    Fungsi
    1.27
    糌
    1.27
    据说
    1.26
     cheminée
    1.23
    Questão
    1.21
     навіть
    1.20
    Maintenant
    1.16
    Activations Density 0.038%

    No Known Activations