© 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. 20391
    Prev
    Next
    INDEX
    Explanations

    punctuation and quotes

    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
    r
    -1.83
    o
    -1.82
    u
    -1.70
    </h2>
    -1.62
    ‪.‬‬
    -1.57
     設計
    -1.47
     вони
    -1.44
    。】
    -1.44
    ኧ
    -1.43
    #--
    -1.42
    POSITIVE LOGITS
     seleccionadas
    1.91
     are
    1.57
     meeste
    1.56
     consideradas
    1.54
     meestal
    1.49
    粜
    1.41
    ’
    1.37
     или
    1.34
     tomadas
    1.34
     escuchadas
    1.32
    Activations Density 0.033%

    No Known Activations