© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13660
    Prev
    Next
    INDEX
    Explanations

    end of phrase punctuation

    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
     gorro
    -2.05
    ,
    -1.89
     for
    -1.85
     that
    -1.77
    なのでしょう
    -1.64
     agujeros
    -1.64
     chaleco
    -1.62
    carne
    -1.59
     suéter
    -1.59
     your
    -1.57
    POSITIVE LOGITS
     extraordin
    1.82
    However
    1.80
    4
    1.80
    ؛
    1.78
    When
    1.78
     useAppContext
    1.73
    ômes
    1.67
    ingly
    1.62
    After
    1.61
     militer
    1.61
    Activations Density 16.942%

    No Known Activations