© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105448
    Prev
    Next
    INDEX
    Explanations

    hours and minutes separator

    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
    ↵
    -3.25
     し
    -2.66
    </u>
    -2.44
    感じです
    -2.34
    a
    -2.33
     is
    -2.25
    м
    -2.22
    ༑
    -2.19
    大的
    -2.17
    焄
    -2.16
    POSITIVE LOGITS
    锘
    2.44
     Kept
    2.22
    已经
    2.17
    佯
    2.14
    讀書
    2.14
    你别
    2.13
    ementara
    2.11
    ‪.‬‬
    2.09
    鬭
    2.09
    而出
    2.08
    Activations Density 0.004%

    No Known Activations