© 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. 101785
    Prev
    Next
    INDEX
    Explanations

    describing typical or conventional things

    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
     because
    -1.99
     through
    -1.95
     when
    -1.95
     three
    -1.74
     also
    -1.60
     at
    -1.60
     two
    -1.58
    When
    -1.56
     five
    -1.55
     four
    -1.52
    POSITIVE LOGITS
    向了
    1.62
     of
    1.57
    indicates
    1.41
    傒
    1.36
    圌
    1.34
    镲
    1.34
     خدمات
    1.27
    THERE
    1.26
    AxisSize
    1.26
    PathParam
    1.23
    Activations Density 0.532%

    No Known Activations