© 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. 9855
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with powers

    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
     emocion
    -1.68
     puedes
    -1.68
     duas
    -1.67
     to
    -1.59
     bereits
    -1.58
     tüm
    -1.57
     ";
    -1.56
    硖
    -1.55
     mucho
    -1.52
     time
    -1.52
    POSITIVE LOGITS
    out
    1.79
    leriyle
    1.70
    i
    1.65
    without
    1.54
     others
    1.53
    al
    1.51
    autres
    1.48
    アンド
    1.46
     ,‬
    1.42
    >
    1.40
    Activations Density 0.003%

    No Known Activations