© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99447
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by 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
    、
    -2.06
     Japão
    -1.90
    $
    -1.84
    ='
    -1.79
    </em>
    -1.75
     samarbeid
    -1.70
    When
    -1.66
    ."
    -1.66
    .'
    -1.62
     brilliant
    -1.62
    POSITIVE LOGITS
     ‘‘
    2.38
     It
    2.05
     ส์
    1.84
    屨
    1.76
    eſ
    1.76
    丷
    1.74
    蹿
    1.73
    撵
    1.69
    ㄉ
    1.65
     revenu
    1.64
    Activations Density 0.018%

    No Known Activations