© 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. 22-GEMMASCOPE-RES-131K
    7. 67639
    Prev
    Next
    INDEX
    Explanations

    South Carolina cities and towns

    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
     Meilleures
    -1.09
     sweter
    -1.04
    
    -1.03
     aeroporto
    -1.02
     choses
    -1.02
     blessé
    -0.98
     mied
    -0.97
    ⎊
    -0.97
     obiet
    -0.96
     moze
    -0.96
    POSITIVE LOGITS
    1
    1.02
    5
    0.99
    6
    0.99
    <eos>
    0.95
    3
    0.94
    7
    0.94
    2
    0.93
    8
    0.92
    4
    0.91
     De
    0.90
    Activations Density 0.001%

    No Known Activations