© 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. 113916
    Prev
    Next
    INDEX
    Explanations

    things appear or occur

    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
     ajouter
    -2.25
    圌
    -2.08
    ౭
    -1.99
    殽
    -1.97
    鸸
    -1.97
    
    -1.95
    帔
    -1.93
     ELEMENTS
    -1.85
    橚
    -1.84
     DAYS
    -1.81
    POSITIVE LOGITS
     With
    2.95
     Usually
    2.47
     What
    2.41
     Several
    2.41
     Often
    2.34
     Basically
    2.34
     These
    2.31
     Since
    2.31
     Considering
    2.28
     Numerous
    2.27
    Activations Density 0.008%

    No Known Activations