© 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. 9165
    Prev
    Next
    INDEX
    Explanations

    findings presented

    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
     also
    -2.11
     know
    -1.73
     now
    -1.67
     también
    -1.59
    也
    -1.57
     would
    -1.45
     Also
    -1.40
     také
    -1.38
     on
    -1.35
     Также
    -1.35
    POSITIVE LOGITS
     飲み
    1.46
    ♪♪
    1.42
     みんな
    1.37
    بسم
    1.34
    ＊＊
    1.30
     pande
    1.29
    なー
    1.28
     裏
    1.28
    無論
    1.28
     kiwi
    1.27
    Activations Density 0.486%

    No Known Activations