© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69689
    Prev
    Next
    INDEX
    Explanations

    course of action or subject

    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
    riezmann
    -1.74
     เพราะ
    -1.73
    giat
    -1.69
    eleste
    -1.67
    :])
    -1.66
    眛
    -1.64
    ῎
    -1.64
    ]};
    -1.62
    zepine
    -1.61
    upol
    -1.60
    POSITIVE LOGITS
    2.11
    2.05
    ↵↵
    1.98
    ❖
    1.88
    						
    1.80
                    
    1.80
                
    1.76
    ть
    1.75
    ar
    1.70
    re
    1.69
    Activations Density 0.009%
    No Known Activations