© 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. 22-GEMMASCOPE-RES-131K
    7. 25247
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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_22/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
     между
    -1.02
     komplette
    -0.97
     hlad
    -0.97
     complementos
    -0.93
    ῾
    -0.89
     acessórios
    -0.88
    ŷ
    -0.87
    ॑
    -0.85
     professionnels
    -0.85
    ᾿
    -0.84
    POSITIVE LOGITS
     by
    1.21
     corrected
    1.05
     correction
    0.98
     correcting
    0.94
     revised
    0.93
     kuhusu
    0.92
     stabilized
    0.89
     вектора
    0.89
     corrections
    0.88
     corrective
    0.88
    Activations Density 0.006%

    No Known Activations