© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57639
    Prev
    Next
    INDEX
    Explanations

    verbs followed by upon

    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
     Baz
    -0.81
    raux
    -0.79
    ceding
    -0.78
    雳
    -0.78
    Baz
    -0.78
    Jamaica
    -0.77
    eze
    -0.77
    irent
    -0.76
     môžete
    -0.74
    baz
    -0.73
    POSITIVE LOGITS
     upon
    1.42
    upon
    1.22
    Upon
    1.10
     UPON
    1.00
     Upon
    1.00
     lider
    0.85
     complained
    0.82
     mediante
    0.82
     prayed
    0.78
     argued
    0.75
    Activations Density 0.053%

    No Known Activations