© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 3634
    Prev
    Next
    INDEX
    Explanations

    names followed by parenthetical roles

    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
    妡
    -1.73
     jugado
    -1.66
     그는
    -1.65
     cumplido
    -1.60
     dibujado
    -1.58
     rempliss
    -1.55
     asegurado
    -1.55
    actéristi
    -1.52
     mía
    -1.49
     trám
    -1.48
    POSITIVE LOGITS
     to
    2.39
     in
    2.03
     as
    1.34
     under
    1.24
     In
    1.22
     If
    1.20
    ͦ
    1.20
     such
    1.14
    in
    1.13
    bucks
    1.13
    Activations Density 0.003%

    No Known Activations