© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108543
    Prev
    Next
    INDEX
    Explanations

    `stay` or `remained`

    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
    ăsp
    -0.78
     funcionamiento
    -0.77
     fără
    -0.76
     interstellar
    -0.75
    .+\
    -0.74
     Montage
    -0.74
    گذ
    -0.72
    зонта
    -0.71
     perdida
    -0.70
     تھا
    -0.70
    POSITIVE LOGITS
     stay
    7.44
    stay
    6.75
     stayed
    6.19
    Stay
    6.13
     staying
    6.13
     Stay
    6.06
     stays
    6.03
     STAY
    5.47
     Staying
    4.84
    STAY
    4.81
    Activations Density 0.171%

    No Known Activations