© 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. 87338
    Prev
    Next
    INDEX
    Explanations

    JSON syntax and code structures

    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
     their
    -2.14
     and
    -1.60
     trova
    -1.50
     ของ
    -1.47
    ním
    -1.45
     these
    -1.45
     Añade
    -1.45
    Ԁ
    -1.41
    늦
    -1.41
    hidro
    -1.40
    POSITIVE LOGITS
    釓
    1.76
    踅
    1.65
     implications
    1.52
    鸶
    1.52
     internetowa
    1.51
    　　《
    1.45
    са
    1.45
    makeConstraints
    1.45
     untersuchen
    1.43
     After
    1.41
    Activations Density 0.112%

    No Known Activations