© 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. 22-GEMMASCOPE-RES-131K
    4. 95649
    Prev
    Next
    INDEX
    Explanations

    2

    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_22/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
     even
    -1.73
     of
    -1.59
     with
    -1.59
     which
    -1.52
     because
    -1.49
     how
    -1.47
     then
    -1.44
     before
    -1.41
     from
    -1.39
     although
    -1.39
    POSITIVE LOGITS
     alcune
    1.33
     vieler
    1.30
     einiger
    1.27
     daardoor
    1.23
     Dinas
    1.20
     andern
    1.19
    有一些
    1.16
    為に
    1.16
     ‚
    1.16
     horrid
    1.16
    Activations Density 0.022%

    No Known Activations