© 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. 113964
    Prev
    Next
    INDEX
    Explanations

    expiration dates and validity

    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
     donnent
    -1.83
    definitely
    -1.77
    comes
    -1.74
    represents
    -1.72
    seems
    -1.67
     )}
    -1.67
    THERE
    -1.66
    ONLY
    -1.65
     」
    -1.63
     ۶
    -1.62
    POSITIVE LOGITS
     would
    1.55
    '
    1.50
     on
    1.48
    siswa
    1.48
     use
    1.47
    e
    1.45
     will
    1.41
    ↵
    1.40
     Providing
    1.40
    ဴ
    1.35
    Activations Density 0.021%

    No Known Activations