© 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. 128142
    Prev
    Next
    INDEX
    Explanations

    HTML elements and structure

    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
     may
    -1.67
     should
    -1.61
     will
    -1.61
    Some
    -1.51
     seems
    -1.43
    *
    -1.37
    There
    -1.35
    "
    -1.34
     seem
    -1.30
     could
    -1.27
    POSITIVE LOGITS
    CHREIB
    1.49
    娲
    1.41
     impresionantes
    1.38
    existent
    1.30
    InputTagHelper
    1.28
    絝
    1.28
    ovým
    1.27
     the
    1.27
     装修
    1.26
    ulates
    1.25
    Activations Density 0.036%

    No Known Activations