© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102280
    Prev
    Next
    INDEX
    Explanations

    numeric values with units

    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
     цветами
    -1.77
    "$_
    -1.59
     Irán
    -1.56
    を目指す
    -1.55
     Informações
    -1.53
    肏
    -1.53
    ………..
    -1.52
    سباب
    -1.52
    ごちそう
    -1.50
    婊
    -1.49
    POSITIVE LOGITS
     извест
    1.67
     ONLY
    1.56
     июня
    1.55
     with
    1.55
    СЯ
    1.53
    辑
    1.50
     июля
    1.49
    fitri
    1.47
    ʏ
    1.45
     mencegah
    1.44
    Activations Density 0.030%

    No Known Activations