© 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. 104384
    Prev
    Next
    INDEX
    Explanations

    sage and maven constructions

    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
    拶
    -2.86
    逦
    -2.78
     dostup
    -2.50
    翃
    -2.47
    のデザイン
    -2.38
     capuche
    -2.34
     uživ
    -2.30
     encontre
    -2.28
    骉
    -2.28
    罽
    -2.25
    POSITIVE LOGITS
    D
    3.09
    If
    3.05
    Ｅ
    2.83
    A
    2.80
    As
    2.77
    C
    2.75
    After
    2.73
    Now
    2.72
    During
    2.69
    At
    2.67
    Activations Density 0.005%

    No Known Activations