© 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. 48532
    Prev
    Next
    INDEX
    Explanations

    HTML headings and "Posted" dates

    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
     falschen
    -1.89
    ție
    -1.88
    </i>
    -1.86
     When
    -1.74
     congreso
    -1.70
     if
    -1.69
    lossians
    -1.67
    ｧ
    -1.59
    电梯
    -1.57
     boasted
    -1.55
    POSITIVE LOGITS
    ༷
    1.84
     \
    1.84
    ’
    1.83
    M
    1.73
     😂
    1.71
    pping
    1.71
    ’，
    1.67
    !!!!!!!
    1.66
     !!!!!
    1.65
    婠
    1.65
    Activations Density 0.010%

    No Known Activations