© 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. 112150
    Prev
    Next
    INDEX
    Explanations

    grew to a size or state

    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
     Making
    -1.93
     removes
    -1.88
     Having
    -1.87
     Being
    -1.86
     makes
    -1.85
     Taking
    -1.80
     Often
    -1.79
     on
    -1.78
     reduces
    -1.78
     Almost
    -1.77
    POSITIVE LOGITS
     startling
    1.88
    苤
    1.77
     soooo
    1.77
     sooo
    1.76
     horrifying
    1.73
     somewhat
    1.73
     ใน
    1.70
     breathtaking
    1.69
     amazingly
    1.69
    ’
    1.68
    Activations Density 0.008%

    No Known Activations