© 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. 128975
    Prev
    Next
    INDEX
    Explanations

    reporting findings from analysis

    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
     have
    -1.78
     each
    -1.72
     using
    -1.72
     used
    -1.66
     while
    -1.64
     and
    -1.64
     was
    -1.58
     With
    -1.55
     ``
    -1.52
     in
    -1.49
    POSITIVE LOGITS
     mojej
    1.68
     guapa
    1.55
    Produit
    1.51
     imponer
    1.45
     peinados
    1.45
     bluz
    1.38
     diamants
    1.38
     baskılı
    1.38
     状態
    1.37
    􏰀
    1.37
    Activations Density 0.137%

    No Known Activations