© 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. 40948
    Prev
    Next
    INDEX
    Explanations

    manchester united, city

    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
    ⴽ
    -2.41
     GOtt
    -2.33
    采用
    -2.33
     放題
    -2.30
    是非常
    -2.16
     ドール
    -2.16
    栳
    -2.13
    ᷆
    -2.13
    ꯸
    -2.13
    .”
    -2.11
    POSITIVE LOGITS
    蓠
    2.88
    .
    2.66
     you
    2.66
     Then
    2.39
    ),
    2.38
     черная
    2.33
     sorta
    2.25
    ită
    2.17
    ):
    2.16
    )-
    2.16
    Activations Density 0.006%

    No Known Activations