© 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. 73936
    Prev
    Next
    INDEX
    Explanations

    main opening parenthesis

    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
     maravilh
    -1.43
     ľudí
    -1.28
    iress
    -1.27
    appears
    -1.25
    nější
    -1.25
     více
    -1.19
    lxt
    -1.19
     vitória
    -1.18
     และ
    -1.17
     regalías
    -1.15
    POSITIVE LOGITS
    撷
    1.19
    (
    1.10
     with
    1.09
    </em>
    1.09
     proj
    1.08
      ……
    1.08
     [],
    
    1.08
     dissu
    1.05
    ولايات
    1.04
    Beberapa
    1.02
    Activations Density 0.001%

    No Known Activations