© 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. 75709
    Prev
    Next
    INDEX
    Explanations

    height and weight measurements

    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
     detaylı
    -1.61
     genellikle
    -1.60
     to
    -1.59
     кілька
    -1.58
    );
    -1.55
    ادن
    -1.52
    pylene
    -1.50
    了一個
    -1.50
     the
    -1.49
    쭉
    -1.47
    POSITIVE LOGITS
    และ
    1.83
     و
    1.80
    rages
    1.74
    fillment
    1.73
     его
    1.73
     и
    1.72
    istani
    1.69
    ícias
    1.67
    tonsoft
    1.66
     فقط
    1.63
    Activations Density 0.004%

    No Known Activations