© 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. 60333
    Prev
    Next
    INDEX
    Explanations

    words starting with un

    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
    渽
    -3.00
    ſu
    -2.72
    盉
    -2.67
     lakukan
    -2.63
    缯
    -2.59
    犼
    -2.52
    楽しんで
    -2.48
    葙
    -2.45
    觧
    -2.41
    鄣
    -2.41
    POSITIVE LOGITS
    <
    2.77
    ኾ
    2.72
     "
    2.64
    鰱
    2.52
    *
    2.47
    啣
    2.39
    исправ
    2.36
    瓛
    2.31
    ’?
    2.27
     вели
    2.23
    Activations Density 0.023%

    No Known Activations