© 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. 34-GEMMASCOPE-RES-131K
    7. 38663
    Prev
    Next
    INDEX
    Explanations

    the Sword in the Stone

    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_34/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
     представля
    -0.90
     conjunction
    -0.70
    线路
    -0.66
    );"
    -0.66
    BackgroundImage
    -0.65
     вы
    -0.65
    出し
    -0.64
    Più
    -0.63
    ỏng
    -0.63
     żeby
    -0.62
    POSITIVE LOGITS
    рованная
    0.92
     culoare
    0.84
     surety
    0.83
    plein
    0.78
    💒
    0.77
    汝
    0.77
     thou
    0.76
     سمع
    0.75
     tiende
    0.75
    卫生
    0.75
    Activations Density 0.138%

    No Known Activations