© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71598
    Prev
    Next
    INDEX
    Explanations

    rounding numbers, ubuntu, foreign words

    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
     tako
    -1.15
     Alpes
    -1.02
    labili
    -1.00
    
    -0.96
    Ultimately
    -0.96
     boli
    -0.95
    ==="
    -0.94
     capot
    -0.93
     cober
    -0.91
     existen
    -0.90
    POSITIVE LOGITS
     imprimé
    1.08
     manquante
    1.08
     międzynarod
    1.05
     suspendu
    1.04
     familières
    1.03
     informatique
    1.02
     häufigsten
    1.01
     rempli
    1.01
     beeintr
    1.01
     trabajador
    1.00
    Activations Density 0.129%

    No Known Activations