© 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. 95702
    Prev
    Next
    INDEX
    Explanations

    INDIANAPOLIS

    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
     supplémentaire
    -1.02
     Apenas
    -1.01
     opis
    -0.96
     kuchen
    -0.96
    Ħ
    -0.95
    neurial
    -0.94
    pholes
    -0.94
    ༣
    -0.94
    ོད་
    -0.93
     jesteśmy
    -0.93
    POSITIVE LOGITS
    ↵↵
    1.41
    εβ
    0.90
    宝贝
    0.88
     ervoor
    0.88
    k
    0.84
     systematically
    0.80
     遇
    0.78
    活用
    0.77
     فبراير
    0.77
    ja
    0.76
    Activations Density 0.002%

    No Known Activations