© 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. 10-GEMMASCOPE-RES-131K
    4. 11679
    Prev
    Next
    INDEX
    Explanations

    industry news and experts

    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
     out
    -1.45
     It
    -1.45
    ;
    
    -1.45
     With
    -1.41
    ጴ
    -1.38
    瀨
    -1.37
     Since
    -1.37
     Álvarez
    -1.35
     otro
    -1.30
     on
    -1.28
    POSITIVE LOGITS
     oock
    1.83
     eenig
    1.72
     industry
    1.71
     deko
    1.70
     hunne
    1.65
    嚒
    1.64
     warszawa
    1.63
    呿
    1.61
     colorear
    1.59
     eenen
    1.58
    Activations Density 0.019%

    No Known Activations