© 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. 35851
    Prev
    Next
    INDEX
    Explanations

    symbols, numbers, and matrix notation

    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
     supermercado
    -0.93
    bigli
    -0.89
    comfortable
    -0.88
    jungle
    -0.86
     apartamentos
    -0.86
    »-
    -0.85
    дает
    -0.85
     stratég
    -0.84
     bordado
    -0.84
     trajes
    -0.83
    POSITIVE LOGITS
    TestBed
    0.98
    学ぶ
    0.97
    links
    0.95
     пев
    0.94
    好看
    0.94
    lla
    0.94
    show
    0.92
    haga
    0.88
     geleg
    0.88
    emp
    0.87
    Activations Density 0.001%

    No Known Activations