© 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. 10-GEMMASCOPE-RES-131K
    7. 90413
    Prev
    Next
    INDEX
    Explanations

    engaged with / by / in

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

    This neuron fires on occurrences of the word “engaged,” especially in mechanical‐engagement contexts.

    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
    塤
    -2.41
    🧌
    -2.36
     extremely
    -2.22
     immense
    -2.16
    
    -2.13
     decidedly
    -2.13
    姈
    -2.13
    巂
    -2.13
     overly
    -2.13
     exceptionally
    -2.13
    POSITIVE LOGITS
    j
    2.52
    e
    2.13
    --
    2.05
    (
    2.00
     When
    1.95
    =
    1.94
     Though
    1.91
    k
    1.88
     Before
    1.87
    h
    1.87
    Activations Density 0.006%

    No Known Activations