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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75266
    Prev
    Next
    INDEX
    Explanations

    angularjs and web development

    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
    0
    -3.08
    Contrary
    -2.50
    ?”
    -2.45
    噲
    -2.41
    Let
    -2.39
    But
    -2.38
    髏
    -2.34
    That
    -2.33
    Efter
    -2.31
     спокойно
    -2.31
    POSITIVE LOGITS
    ng
    3.55
    翕
    2.92
    我都
    2.52
     \"
    2.44
     of
    2.41
    い
    2.38
     führten
    2.34
     ließen
    2.33
     fickle
    2.31
     machten
    2.25
    Activations Density 0.006%

    No Known Activations