© 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. 29050
    Prev
    Next
    INDEX
    Explanations

    poker hands

    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
    </u>
    -1.66
    </h3>
    -1.53
     ?',
    -1.45
    k
    -1.32
     люди
    -1.31
     Hälfte
    -1.30
     \
    -1.29
     filmi
    -1.28
     ";
    -1.27
     '))
    -1.27
    POSITIVE LOGITS
    杁
    1.73
     seguía
    1.66
     falleció
    1.60
     resultó
    1.59
    𓁹
    1.59
     cualquiera
    1.57
    emporio
    1.55
     sufficiently
    1.54
     sufri
    1.51
     regresó
    1.51
    Activations Density 0.010%

    No Known Activations