© 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. 57506
    Prev
    Next
    INDEX
    Explanations

    Ge followed by letters

    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
    𐑂
    -3.05
    “
    -2.72
    鋱
    -2.69
    ある
    -2.66
    lossians
    -2.63
     voor
    -2.44
    ㈬
    -2.36
    
    -2.36
    which
    -2.30
    та
    -2.27
    POSITIVE LOGITS
    D
    2.47
     \
    2.42
     ''
    2.39
     состоит
    2.38
    いている
    2.34
    ってしまう
    2.27
     проекта
    2.25
    嫻
    2.23
    ходить
    2.22
     ‘‘
    2.20
    Activations Density 0.004%

    No Known Activations