© 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. 19425
    Prev
    Next
    INDEX
    Explanations

    bending and appending

    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
    蹋
    -2.53
     сотрудники
    -2.44
     δή
    -2.39
    人の
    -2.36
     quarrel
    -2.30
     dari
    -2.28
    </strong>
    -2.28
    and
    -2.28
     veteran
    -2.27
    1
    -2.27
    POSITIVE LOGITS
    鸶
    3.45
    骓
    3.00
    摭
    2.86
    摇了
    2.80
    脔
    2.72
    灕
    2.69
    kwür
    2.64
     =
    2.64
    欵
    2.59
    Ꭳ
    2.55
    Activations Density 0.005%

    No Known Activations