© 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. 22-GEMMASCOPE-RES-131K
    7. 28636
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

    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
    靱
    -1.34
    :
    -1.18
    靭
    -1.17
    ш
    -1.05
     сзади
    -1.05
    e
    -1.04
    щите
    -1.01
    David
    -1.01
    ž
    -1.01
    作品の
    -1.00
    POSITIVE LOGITS
     vergüenza
    1.24
     paura
    1.15
    なのかな
    1.11
     garanzia
    1.06
     leggero
    1.04
     ソックス
    1.04
     facturas
    1.03
     sensaciones
    1.03
     hebben
    1.02
    Lille
    1.02
    Activations Density 0.019%

    No Known Activations