© 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. 61190
    Prev
    Next
    INDEX
    Explanations

    films and artists

    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>
    -1.48
     for
    -1.44
    <tr>
    -1.42
     并
    -1.41
    君は
    -1.37
     …..
    -1.33
    ……..
    -1.25
     !!!!
    -1.25
    RESUMO
    -1.24
    </h3>
    -1.23
    POSITIVE LOGITS
     those
    1.52
     only
    1.38
    Galería
    1.32
     aquellos
    1.31
    Adverten
    1.30
    Those
    1.26
    Ketua
    1.26
    jsxFileName
    1.20
     ご飯
    1.20
    Edición
    1.19
    Activations Density 0.305%

    No Known Activations