© 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. 9859
    Prev
    Next
    INDEX
    Explanations

    describing states and characteristics

    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
     einzigartige
    -1.68
     erforder
    -1.66
     dergleichen
    -1.64
    鱟
    -1.59
     επίσης
    -1.59
     myös
    -1.58
     også
    -1.57
     också
    -1.55
     también
    -1.55
     również
    -1.53
    POSITIVE LOGITS
     of
    1.66
     if
    1.62
    .
    1.44
     after
    1.39
    ;
    1.36
    likle
    1.34
     or
    1.30
     although
    1.30
     option
    1.30
     E
    1.30
    Activations Density 1.195%

    No Known Activations