© 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. 34-GEMMASCOPE-RES-131K
    4. 73425
    Prev
    Next
    INDEX
    Explanations

    people staying at places

    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_34/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
    ální
    -0.71
     fluores
    -0.69
    阱
    -0.68
    합니다
    -0.67
     подвер
    -0.67
    setcounter
    -0.66
    邢
    -0.66
     пережи
    -0.65
    inado
    -0.65
     jel
    -0.65
    POSITIVE LOGITS
     stay
    6.03
     staying
    5.88
    stay
    5.41
    Stay
    4.91
     stayed
    4.91
     stays
    4.81
     Stay
    4.72
     Staying
    4.41
    Staying
    4.41
     STAY
    4.19
    Activations Density 0.051%

    No Known Activations