© 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. 127384
    Prev
    Next
    INDEX
    Explanations

    material composition elements

    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
    tized
    -1.36
    罠
    -1.35
     analis
    -1.30
     članak
    -1.30
    SafeArea
    -1.28
     one
    -1.27
    ↵↵
    -1.24
    ūsų
    -1.23
     производства
    -1.23
     darin
    -1.21
    POSITIVE LOGITS
     cuando
    1.58
    Etape
    1.40
    2
    1.31
     ribuan
    1.30
     ویتامین
    1.28
    其他
    1.27
     必要
    1.27
    aigu
    1.26
    various
    1.25
    vidéo
    1.25
    Activations Density 0.027%

    No Known Activations