© 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. 45494
    Prev
    Next
    INDEX
    Explanations

    object property access

    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
    Negative Logits
     it
    -1.69
     in
    -1.68
     misschien
    -1.31
     pokud
    -1.31
    essere
    -1.29
    它是
    -1.27
     belki
    -1.26
     at
    -1.21
     jeśli
    -1.20
     if
    -1.18
    POSITIVE LOGITS
    .
    1.54
     cuyos
    1.54
     maceta
    1.52
    
    1.43
     determinados
    1.43
    鹛
    1.41
    擻
    1.40
    GIVEREF
    1.37
    ਖ਼
    1.37
     orgánico
    1.35
    Activations Density 0.011%

    No Known Activations