© 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. 10-GEMMASCOPE-RES-131K
    4. 19246
    Prev
    Next
    INDEX
    Explanations

    "z's"

    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_10/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
    </h2>
    -2.05
     by
    -1.80
    </sup>
    -1.63
     through
    -1.58
    瑧
    -1.56
     an
    -1.55
    </em>
    -1.55
    節約
    -1.52
     concerning
    -1.52
    ละเอ
    -1.52
    POSITIVE LOGITS
    歺
    1.81
     Infór
    1.77
    '
    1.76
     البرنامج
    1.75
     Mientras
    1.70
    ";
    
    1.67
    來到
    1.66
    hasilkan
    1.63
    aughter
    1.59
     Obten
    1.59
    Activations Density 0.021%

    No Known Activations