© 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. 71027
    Prev
    Next
    INDEX
    Explanations

    U-shape or U-shaped objects

    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
    可以
    -2.80
    已经
    -2.61
    2
    -2.31
    应该
    -2.27
    1
    -2.25
    如果
    -2.25
    '
    -2.22
    知道
    -2.19
    C
    -2.17
    就是
    -2.13
    POSITIVE LOGITS
    ᚔ
    2.11
    鶺
    2.02
    iffance
    1.95
    ᯾
    1.91
    UCIÓN
    1.91
    カッコ
    1.88
    ⎆
    1.88
     kırmızı
    1.88
     extremadamente
    1.88
    峁
    1.88
    Activations Density 0.005%

    No Known Activations