© 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. 10-GEMMASCOPE-RES-131K
    7. 124106
    Prev
    Next
    INDEX
    Explanations

    natural states and processes

    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_10/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
    НИЯ
    -1.53
    janje
    -1.48
    </strong>
    -1.47
    grès
    -1.45
    AGUA
    -1.38
    ZIONE
    -1.37
    ᠬ
    -1.36
    }$
    -1.35
    createCell
    -1.34
    
    -1.34
    POSITIVE LOGITS
    ↵
    2.27
    However
    1.62
     rique
    1.52
    A
    1.46
    lardan
    1.45
     
    1.37
    b
    1.33
     harsh
    1.31
    下さい
    1.29
     burada
    1.29
    Activations Density 0.050%

    No Known Activations