© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118599
    Prev
    Next
    INDEX
    Explanations

    software test cases

    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_34/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
     pierna
    -0.91
     politiker
    -0.89
    wirkung
    -0.89
    處理
    -0.88
     strö
    -0.87
    查詢
    -0.86
     线条
    -0.85
    リット
    -0.85
     ángeles
    -0.85
     çiz
    -0.84
    POSITIVE LOGITS
     test
    2.41
     tests
    2.39
     testing
    1.85
     Tests
    1.64
     Test
    1.58
    Tests
    1.55
    test
    1.46
    Test
    1.44
    junit
    1.43
    tests
    1.43
    Activations Density 0.100%

    No Known Activations