© 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. 59864
    Prev
    Next
    INDEX
    Explanations

    various languages and programming constructs

    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>
    -2.41
    c
    -1.74
    k
    -1.60
    i
    -1.57
    Then
    -1.52
    si
    -1.47
    l
    -1.46
    m
    -1.46
    u
    -1.45
     of
    -1.41
    POSITIVE LOGITS
     to
    1.86
    ݯ
    1.71
    alamualaikum
    1.67
    partir
    1.66
    droj
    1.61
    
    1.60
    olved
    1.60
     квартире
    1.59
     própri
    1.58
    }`);
    1.56
    Activations Density 0.015%

    No Known Activations