© 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. 72872
    Prev
    Next
    INDEX
    Explanations

    years

    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
    ensões
    -1.65
    assium
    -1.61
     दोनों
    -1.49
     眼睛
    -1.48
     two
    -1.45
     sabid
    -1.44
    出来的
    -1.40
    と言われる
    -1.38
    喱
    -1.35
    ascin
    -1.34
    POSITIVE LOGITS
    th
    1.72
    <sup>
    1.49
     Donc
    1.41
     of
    1.41
     têm
    1.40
     "
    1.39
    ៖
    1.38
    の人に
    1.37
    ()?.
    1.37
    ➚
    1.34
    Activations Density 0.015%

    No Known Activations