© 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. 34-GEMMASCOPE-RES-131K
    7. 48405
    Prev
    Next
    INDEX
    Explanations

    form used for pouring

    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
     riveted
    -0.80
    gner
    -0.73
     Prefix
    -0.73
    Teachers
    -0.72
     toasted
    -0.72
     päät
    -0.71
     gardeners
    -0.71
     oath
    -0.70
     siècle
    -0.69
     Piero
    -0.68
    POSITIVE LOGITS
     placing
    1.23
     pouring
    1.19
     pour
    1.08
     poured
    1.05
    Pour
    1.02
     Pour
    1.02
     placement
    1.02
     POUR
    1.00
     lait
    1.00
     pours
    0.94
    Activations Density 0.030%

    No Known Activations