© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101899
    Prev
    Next
    INDEX
    Explanations

    waiting in line

    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
    .
    -2.47
    What
    -2.23
     .
    -2.05
    Why
    -1.98
    How
    -1.96
    ↵
    -1.94
    3
    -1.78
    but
    -1.77
    Are
    -1.69
    Here
    -1.64
    POSITIVE LOGITS
    новение
    1.83
    '
    1.69
     for
    1.60
     kwenye
    1.59
    歃
    1.57
    ){$
    1.52
    鼉
    1.52
    蟜
    1.50
    壜
    1.49
    
    1.48
    Activations Density 0.024%

    No Known Activations