© 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. 827
    Prev
    Next
    INDEX
    Explanations

    configuration files

    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
    لقاء
    -1.58
     gezicht
    -1.39
    ieR
    -1.35
    瑞典
    -1.34
    全集
    -1.31
    蜃
    -1.31
    yyj
    -1.30
    姥
    -1.28
    Gén
    -1.28
     ovviamente
    -1.28
    POSITIVE LOGITS
    8
    1.69
     -
    1.54
    6
    1.52
    7
    1.50
    My
    1.42
    两个
    1.39
    What
    1.38
    THE
    1.36
    И
    1.35
    Ф
    1.34
    Activations Density 0.021%

    No Known Activations