© 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. 10526
    Prev
    Next
    INDEX
    Explanations

    followed by on

    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
    ༑
    -2.73
    龇
    -2.56
    Ꮠ
    -2.50
    鹀
    -2.39
    ⟣
    -2.39
    艄
    -2.38
    ⎔
    -2.36
    ਗ਼
    -2.34
    
    -2.31
    Ꭳ
    -2.28
    POSITIVE LOGITS
     on
    3.13
    .
    2.91
    s
    2.53
    あります
    2.30
    也
    2.25
     Jugendliche
    2.20
    .”
    2.17
    ”,
    2.17
    ),
    2.16
    可能
    2.11
    Activations Density 0.107%

    No Known Activations