© 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. 22-GEMMASCOPE-RES-131K
    7. 68498
    Prev
    Next
    INDEX
    Explanations

    actions indicating ongoing processes

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

    The neuron selectively fires on “-ing” forms of dynamic, event-describing verbs (gerunds/present-participles indicating actions or state changes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     may
    -1.60
     could
    -1.57
     might
    -1.54
     started
    -1.50
     seems
    -1.48
     did
    -1.48
    が
    -1.48
     does
    -1.47
     fusca
    -1.44
     went
    -1.43
    POSITIVE LOGITS
    すっ
    2.08
    ほら
    2.08
    あー
    1.98
    えっ
    1.98
    からお
    1.98
    あぁ
    1.98
    だけではなく
    1.95
    ほんと
    1.85
    へ行
    1.84
    ほんとに
    1.84
    Activations Density 0.039%

    No Known Activations