© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 110575
    Prev
    Next
    INDEX
    Explanations

    list(c(...))

    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
     to
    -2.94
    </h2>
    -2.23
     ошибка
    -1.69
    にとっては
    -1.67
    </h4>
    -1.62
     dovr
    -1.55
    婓
    -1.55
    puestas
    -1.52
    us
    -1.51
    鮠
    -1.48
    POSITIVE LOGITS
     \
    1.88
    ksessa
    1.66
     algunas
    1.56
     algunos
    1.54
     the
    1.54
    ."
    1.53
     تعدى
    1.50
    翃
    1.46
     =
    1.43
    美国的
    1.42
    Activations Density 0.004%

    No Known Activations