© 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. 416
    Prev
    Next
    INDEX
    Explanations

    code and technical descriptions

    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
     its
    -1.13
    XCTAssertEqual
    -0.96
     each
    -0.91
     أنها
    -0.91
     to
    -0.90
     พร
    -0.87
     noiva
    -0.87
     any
    -0.87
    clearInterval
    -0.85
    Elaboración
    -0.84
    POSITIVE LOGITS
     Perſ
    1.02
     relojes
    1.00
     например
    1.00
     périodes
    0.94
     новый
    0.91
     периода
    0.91
    future
    0.90
     kilom
    0.90
    эле
    0.89
     diseñados
    0.87
    Activations Density 0.004%

    No Known Activations