© 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. 34-GEMMASCOPE-RES-131K
    4. 75407
    Prev
    Next
    INDEX
    Explanations

    ease, fast, Quality

    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
    ふと
    -0.91
     DUKE
    -0.90
     скриншот
    -0.88
    のだろう
    -0.85
    こいつ
    -0.84
     pokrač
    -0.83
     gigantic
    -0.82
    AMILTON
    -0.81
    genodigd
    -0.80
     exhilarating
    -0.80
    POSITIVE LOGITS
     ease
    0.97
    ادة
    0.77
     before
    0.75
     demonstrate
    0.75
    즘
    0.73
    ồi
    0.73
    ebel
    0.72
     February
    0.72
     pointy
    0.71
     should
    0.71
    Activations Density 0.019%

    No Known Activations