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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35031
    Prev
    Next
    INDEX
    Explanations

    ranking numbers and achievements

    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
    ificato
    -1.06
    stwa
    -0.99
    dentes
    -0.97
     tandis
    -0.95
     things
    -0.91
     it
    -0.91
     rather
    -0.90
    خي
    -0.89
    Certain
    -0.85
    тной
    -0.83
    POSITIVE LOGITS
     uppdater
    1.25
     fortfarande
    1.19
     hoppas
    1.18
    造型
    1.10
     fortsätter
    1.09
     hjälper
    1.04
     varje
    1.02
     arbetar
    1.02
     förslag
    1.02
     samarbeid
    1.01
    Activations Density 0.018%

    No Known Activations