© 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. 86680
    Prev
    Next
    INDEX
    Explanations

    directory navigation

    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
    In
    -2.17
     gröss
    -1.89
     geprü
    -1.89
     äusser
    -1.82
     tatsäch
    -1.80
    しています
    -1.80
     notwendi
    -1.79
     a
    -1.79
     jähr
    -1.79
     he
    -1.73
    POSITIVE LOGITS
    😍😍
    1.97
    👍👍
    1.79
    💀
    1.77
    ✌
    1.77
    👍🏻
    1.73
    ☺️
    1.70
    😌
    1.69
    '
    1.68
     OXFORD
    1.66
    🫣
    1.66
    Activations Density 0.007%

    No Known Activations