© 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. 130581
    Prev
    Next
    INDEX
    Explanations

    list items, bullet points

    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
     with
    -2.23
     more
    -2.06
     as
    -2.02
     that
    -2.02
     in
    -2.00
     or
    -1.97
     its
    -1.91
     continue
    -1.86
    l
    -1.84
     even
    -1.83
    POSITIVE LOGITS
    ਗ਼
    2.67
    ⁛
    2.30
     obed
    2.27
     oce
    2.25
    
    2.25
    ктором
    2.23
     consci
    2.23
    KommentareTeilen
    2.19
    ٧
    2.19
    瞟
    2.17
    Activations Density 0.009%

    No Known Activations