© 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. 22-GEMMASCOPE-RES-131K
    7. 35072
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
     such
    -1.02
    やお
    -1.00
     좋은
    -0.94
    来週
    -0.91
    Gör
    -0.90
    cillary
    -0.90
    elts
    -0.89
    isEqualTo
    -0.88
    Expert
    -0.87
    -0.87
    POSITIVE LOGITS
    dieu
    0.98
     augusti
    0.94
    もちろん
    0.93
    venta
    0.92
    Править
    0.90
    romas
    0.90
     veril
    0.90
     Edizioni
    0.89
    味が
    0.88
     được
    0.88
    Activations Density 0.012%

    No Known Activations