© 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. 68822
    Prev
    Next
    INDEX
    Explanations

    complexion descriptions

    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
    逦
    -2.97
    
    -2.88
    ’:
    -2.80
    ”:
    -2.78
    ”;
    -2.70
    随之
    -2.69
     seorang
    -2.59
    ”—
    -2.53
    …」
    -2.50
    がついて
    -2.48
    POSITIVE LOGITS
     и
    2.83
    是
    2.80
    3
    2.61
     He
    2.50
     和
    2.47
    7
    2.47
    或者
    2.44
    就是
    2.44
    0
    2.38
     可以
    2.36
    Activations Density 0.007%

    No Known Activations