© 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. 105396
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     fragte
    -1.48
     wollt
    -1.23
    德國
    -1.23
    西班牙
    -1.20
    يف
    -1.16
     télécommande
    -1.14
     penghargaan
    -1.13
    摃
    -1.13
    Using
    -1.11
     machten
    -1.11
    POSITIVE LOGITS
    </td>
    1.48
     ihre
    1.45
    馀
    1.42
    ednesdays
    1.40
    violent
    1.24
    dersfield
    1.23
     back
    1.21
    籥
    1.21
     ComVisible
    1.20
    返し
    1.20
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.