© 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. 60814
    Prev
    Next
    INDEX
    Explanations

    sports equipment

    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
    骓
    -1.48
     hidupnya
    -1.38
    躑
    -1.38
    criptures
    -1.34
    鸨
    -1.31
    囪
    -1.31
    d
    -1.29
    辈子
    -1.29
     boar
    -1.28
     ifrån
    -1.28
    POSITIVE LOGITS
     löst
    1.84
     valgt
    1.56
    翆
    1.54
     budding
    1.51
    岨
    1.50
    Early
    1.48
    Look
    1.47
    珵
    1.46
     longtime
    1.45
    ྜ
    1.44
    Activations Density 0.019%

    No Known Activations