© 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. 44220
    Prev
    Next
    INDEX
    Explanations

    comment markers or code start

    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
     diminuer
    -1.45
     both
    -1.43
     eliminar
    -1.39
     ścian
    -1.35
     intenta
    -1.35
     दोनों
    -1.34
     både
    -1.34
     transcur
    -1.34
     zarówno
    -1.33
     empêcher
    -1.33
    POSITIVE LOGITS
     so
    1.41
     águas
    1.27
    我们
    1.21
    เรา
    1.20
    尔的
    1.18
     azzurro
    1.18
     with
    1.17
     zucca
    1.16
     ceva
    1.16
     we
    1.14
    Activations Density 0.000%

    No Known Activations