© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15514
    Prev
    Next
    INDEX
    Explanations

    ending 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
     modelleri
    -1.74
     системой
    -1.72
     yapılır
    -1.69
     With
    -1.68
     gerekir
    -1.66
     élar
    -1.65
    ieteur
    -1.61
     высокая
    -1.60
    龊
    -1.59
    場は
    -1.59
    POSITIVE LOGITS
    ’
    2.02
     \
    1.74
    -
    1.73
    iffance
    1.67
     during
    1.66
    </strong>
    1.52
     surprising
    1.50
     aventures
    1.49
     we
    1.48
     kwi
    1.47
    Activations Density 0.056%

    No Known Activations