© 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. 10-GEMMASCOPE-RES-131K
    7. 103637
    Prev
    Next
    INDEX
    Explanations

    install location or item

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires on imperative instructional phrases—especially UI‐navigation or setup steps (e.g. “Select…,” “Open…,” “Create…,” “Browse…”) in a step‐by‐step guide.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Their
    -2.34
     they
    -1.99
     их
    -1.97
     lorsque
    -1.94
     their
    -1.94
     jejich
    -1.90
    They
    -1.87
     leur
    -1.81
    llac
    -1.80
     Their
    -1.77
    POSITIVE LOGITS
     to
    1.88
     your
    1.74
     then
    1.59
     from
    1.59
     in
    1.59
     itong
    1.45
     pomocou
    1.43
     again
    1.42
     hanggang
    1.42
    忆
    1.34
    Activations Density 0.270%

    No Known Activations