© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11541
    Prev
    Next
    INDEX
    Explanations

    U.S. Patent applications

    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
     methods
    -1.05
     Speisen
    -1.02
     exé
    -1.02
    ススメ
    -1.00
    ıldı
    -0.98
    buffered
    -0.97
     DÍA
    -0.97
     activities
    -0.97
    duras
    -0.96
     dedans
    -0.96
    POSITIVE LOGITS
    Rote
    1.17
    同じ
    1.13
    ymmetry
    1.05
    Hü
    1.05
    Fonto
    1.02
    と
    0.98
     एवं
    0.98
     успешно
    0.97
     dimana
    0.96
    Frei
    0.96
    Activations Density 0.002%

    No Known Activations