© 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. 42473
    Prev
    Next
    INDEX
    Explanations

    t-shirt

    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
    7
    -2.88
    1
    -2.66
     —
    -2.64
     are
    -2.53
    2
    -2.41
     Would
    -2.41
    或
    -2.36
    8
    -2.33
    在我
    -2.31
    </sup>
    -2.27
    POSITIVE LOGITS
    鈇
    2.67
    🙆
    2.63
    🍺
    2.59
    🍻
    2.56
    ଫ
    2.53
     "
    2.50
    💋
    2.48
     menek
    2.45
    🍷
    2.44
    🎉
    2.41
    Activations Density 0.005%

    No Known Activations