© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14925
    Prev
    Next
    INDEX
    Explanations

    http://

    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_22/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
     cál
    -1.09
    美味し
    -1.06
     pymongo
    -0.99
    athed
    -0.98
    arition
    -0.97
    おかしい
    -0.96
    美味しそう
    -0.94
     път
    -0.94
     zostanie
    -0.88
    很大的
    -0.88
    POSITIVE LOGITS
     www
    1.04
    www
    0.96
    🙋
    0.96
     think
    0.91
     would
    0.88
     nacidos
    0.88
    зви
    0.85
     autorité
    0.84
     discí
    0.84
    😐
    0.84
    Activations Density 0.064%

    No Known Activations