© 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. 42307
    Prev
    Next
    INDEX
    Explanations

    applies to

    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
    🎶
    -1.69
    aziland
    -1.59
    нение
    -1.57
    avano
    -1.56
    ristan
    -1.52
     '))
    -1.50
    iul
    -1.48
    ！"
    -1.44
    нгредієнти
    -1.44
    жнему
    -1.44
    POSITIVE LOGITS
    4
    2.23
    0
    2.20
    1
    2.19
    2
    2.09
     you
    1.98
    8
    1.95
    7
    1.92
    3
    1.91
    6
    1.77
    ).
    1.66
    Activations Density 0.023%

    No Known Activations