© 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. 130442
    Prev
    Next
    INDEX
    Explanations

    common connector followed by specific noun

    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
     gefunden
    -1.02
    uating
    -1.00
    Gilla
    -0.98
    Élet
    -0.98
    itize
    -0.97
    itively
    -0.97
    essere
    -0.97
    inerary
    -0.96
    asyon
    -0.96
    fordshire
    -0.95
    POSITIVE LOGITS
     Hül
    0.98
    によっては
    0.96
     after
    0.94
    好在
    0.93
     Other
    0.93
     Få
    0.92
     县
    0.88
    하며
    0.88
    after
    0.87
     কো
    0.85
    Activations Density 0.077%

    No Known Activations