© 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. 71437
    Prev
    Next
    INDEX
    Explanations

    imports and file operations

    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
     escritora
    -0.94
    と呼ばれる
    -0.93
     totalité
    -0.93
    regard
    -0.90
    −/−
    -0.89
    ostasis
    -0.89
     daban
    -0.89
    
    -0.88
    蓼
    -0.88
     waardoor
    -0.87
    POSITIVE LOGITS
    行政区划
    1.07
     Germany
    0.97
     これ
    0.95
    adze
    0.94
    ULTS
    0.92
     such
    0.91
    HE
    0.90
    alanx
    0.90
    يح
    0.89
    SK
    0.86
    Activations Density 0.002%

    No Known Activations