© 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. 12433
    Prev
    Next
    INDEX
    Explanations

    function calls and assignments

    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
     wszystkich
    -1.15
    饜
    -1.03
     followed
    -1.02
     творчества
    -0.98
     Multiplayer
    -0.95
     メニュー
    -0.94
     tsl
    -0.94
     ij
    -0.93
     africa
    -0.93
     ");
    -0.93
    POSITIVE LOGITS
     menyes
    1.13
     their
    1.12
    their
    1.05
    there
    1.02
     Unless
    0.99
     То
    0.99
     mariée
    0.97
     what
    0.96
     any
    0.93
    龚
    0.93
    Activations Density 0.004%

    No Known Activations