© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84326
    Prev
    Next
    INDEX
    Explanations

    importing libraries and frameworks

    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
     --
    -0.94
     any
    -0.93
    ....
    -0.91
     konnten
    -0.90
     informatique
    -0.90
     all
    -0.89
     you
    -0.88
     to
    -0.88
     which
    -0.88
     as
    -0.87
    POSITIVE LOGITS
     conster
    1.01
     kanker
    0.92
     imobili
    0.91
    Them
    0.91
     drap
    0.89
     garder
    0.89
     vernis
    0.86
     droog
    0.85
     zel
    0.85
    儅
    0.84
    Activations Density 0.004%

    No Known Activations