© 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. 104506
    Prev
    Next
    INDEX
    Explanations

    choice and selection

    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
     also
    -1.03
     courtship
    -0.94
     roommates
    -0.90
     is
    -0.89
     teaches
    -0.86
     الأخرى
    -0.85
     joins
    -0.83
    观众
    -0.82
    聳
    -0.82
    '"
    -0.81
    POSITIVE LOGITS
     выбира
    1.01
    Naturally
    1.00
     reprises
    0.98
    選ば
    0.97
    显然
    0.97
     scegliere
    0.96
    lieving
    0.95
     والتي
    0.93
     selezion
    0.92
     Naturally
    0.91
    Activations Density 0.064%

    No Known Activations