© 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. 95444
    Prev
    Next
    INDEX
    Explanations

    expressing preference or choice

    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
     some
    -1.13
    Приятного
    -1.05
    sapat
    -1.05
    Меня
    -1.05
    İstin
    -1.03
    Цели
    -1.00
    狛
    -0.97
    Ширина
    -0.96
    的一些
    -0.95
    Beberapa
    -0.94
    POSITIVE LOGITS
     prefer
    1.34
     preferring
    1.11
    prefer
    1.05
     inkább
    1.04
     beide
    1.04
    どちら
    1.04
     latter
    1.02
     favoring
    1.02
    Prefer
    0.99
     beiden
    0.98
    Activations Density 0.059%

    No Known Activations