© 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. 72057
    Prev
    Next
    INDEX
    Explanations

    programming declarations

    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
     possibilité
    -1.43
     toils
    -1.38
     appris
    -1.38
    ︲
    -1.37
     unwarran
    -1.37
     terá
    -1.36
    妧
    -1.34
    www
    -1.34
     subordin
    -1.33
     exhort
    -1.30
    POSITIVE LOGITS
     this
    1.71
     yesterday
    1.62
     なく
    1.46
     themselves
    1.45
    即
    1.43
     gentlemen
    1.41
    الی
    1.41
     both
    1.38
    -“
    1.38
     –
    1.36
    Activations Density 0.002%

    No Known Activations