© 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. 265
    Prev
    Next
    INDEX
    Explanations

    function and method calls

    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
     ſever
    -1.80
     différents
    -1.73
     diſt
    -1.67
     различных
    -1.59
    嵓
    -1.55
     ſmall
    -1.53
     verschillende
    -1.52
     unſ
    -1.51
     leſs
    -1.51
     choisir
    -1.48
    POSITIVE LOGITS
     which
    2.06
     (
    1.95
     with
    1.83
     that
    1.77
     on
    1.56
     two
    1.48
     will
    1.48
     this
    1.45
     from
    1.40
     one
    1.38
    Activations Density 0.024%

    No Known Activations