© 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. 131067
    Prev
    Next
    INDEX
    Explanations

    Louis Vuitton, Arjun, Miklos

    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
    里有
    -2.05
    -
    -2.02
     crux
    -1.95
    /
    -1.91
    していた
    -1.91
     With
    -1.91
    .'
    -1.90
     "\\
    -1.88
     娘
    -1.84
    谘
    -1.84
    POSITIVE LOGITS
    '
    2.52
    屃
    2.44
     \
    2.20
    läufig
    2.09
     erhi
    2.09
     eenen
    2.06
     uda
    2.06
     equipado
    2.05
    巂
    2.02
     fote
    1.98
    Activations Density 0.002%

    No Known Activations