© 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. 104255
    Prev
    Next
    INDEX
    Explanations

    relation =

    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
     inond
    -2.95
    窳
    -2.88
     fermer
    -2.88
    ᚻ
    -2.84
     économie
    -2.83
    蹰
    -2.81
    ꯷
    -2.78
     motivi
    -2.78
     humeur
    -2.77
     acheter
    -2.75
    POSITIVE LOGITS
    “
    3.27
    </em>
    2.92
     Normally
    2.88
    ↵↵↵
    2.83
     For
    2.75
     Much
    2.75
     Notably
    2.72
    所以在
    2.72
     Particularly
    2.72
    er
    2.72
    Activations Density 0.013%

    No Known Activations