© 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. 118532
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structures

    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
     rosario
    -0.87
     within
    -0.82
     half
    -0.78
     mainly
    -0.78
     beginning
    -0.78
     lead
    -0.78
     got
    -0.78
    psfrag
    -0.77
     been
    -0.77
     except
    -0.76
    POSITIVE LOGITS
     pomys
    0.91
    bemos
    0.90
     raccomand
    0.89
    関連リンク
    0.89
    ,}
    0.88
    usepackage
    0.88
     produktu
    0.87
    hängig
    0.85
    circled
    0.85
    منابع
    0.85
    Activations Density 0.001%

    No Known Activations