© 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. 102011
    Prev
    Next
    INDEX
    Explanations

    maintenance work or issues

    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
    鼉
    -2.80
    琑
    -2.78
    鬭
    -2.73
    ため
    -2.58
     dengan
    -2.53
    栳
    -2.33
    缑
    -2.31
     There
    -2.30
    詎
    -2.30
    孥
    -2.28
    POSITIVE LOGITS
    ↵
    3.42
     моя
    2.84
    杳
    2.77
    逡
    2.67
    摭
    2.64
    愉快
    2.52
    alamus
    2.48
    趼
    2.48
     jedes
    2.48
    をする
    2.48
    Activations Density 0.003%

    No Known Activations