© 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. 57385
    Prev
    Next
    INDEX
    Explanations

    Is there any way

    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
    磻
    -1.88
    糶
    -1.88
     sprüche
    -1.86
    ᯾
    -1.85
     facendo
    -1.83
    喾
    -1.81
    婓
    -1.74
    ate
    -1.72
     ewigen
    -1.70
    ۠
    -1.70
    POSITIVE LOGITS
    </strong>
    2.06
     $
    1.92
    onomian
    1.81
     This
    1.80
     important
    1.71
     \
    1.61
     indication
    1.61
    是怎么回事
    1.60
    elerik
    1.60
     $(
    1.55
    Activations Density 0.015%

    No Known Activations