© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113111
    Prev
    Next
    INDEX
    Explanations

    full followed by noun

    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
     \
    -1.50
    ↵↵
    -1.47
     (
    -1.37
     „
    -1.34
     "
    -1.28
     común
    -1.28
     &
    -1.27
     “
    -1.26
    </th>
    -1.20
    </td>
    -1.19
    POSITIVE LOGITS
    full
    1.97
     full
    1.85
    Full
    1.75
    ネー
    1.56
    最後まで
    1.48
     ayakkabı
    1.46
     samh
    1.45
     полной
    1.45
     magasiner
    1.41
     dikembangkan
    1.38
    Activations Density 0.144%

    No Known Activations