© 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. 20165
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or code symbols

    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
    
    -2.59
    ᯾
    -2.52
     caído
    -2.38
    蚋
    -2.36
     you
    -2.27
    您的
    -2.23
    穑
    -2.20
    ଢ
    -2.16
     színes
    -2.16
    我們的
    -2.16
    POSITIVE LOGITS
    al
    3.02
    y
    2.75
    l
    2.67
    X
    2.64
    et
    2.56
    g
    2.53
    H
    2.48
    at
    2.44
    ).
    2.42
    <bos>
    2.36
    Activations Density 0.000%

    No Known Activations