© 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. 10-GEMMASCOPE-RES-131K
    4. 10335
    Prev
    Next
    INDEX
    Explanations

    a few weeks

    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
     Octobre
    -2.20
    [
    
    -2.19
    อยาก
    -2.11
     Septembre
    -2.09
     desember
    -1.98
    ARIES
    -1.97
     fauteuil
    -1.93
     "?"
    -1.92
    GLAS
    -1.90
    🐝
    -1.89
    POSITIVE LOGITS
     there
    2.30
     by
    2.30
     any
    2.28
     suitable
    2.17
     it
    2.09
     new
    2.06
     different
    2.00
     \
    1.98
     necessary
    1.98
     we
    1.95
    Activations Density 0.000%

    No Known Activations