© 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. 84327
    Prev
    Next
    INDEX
    Explanations

    professions and their actions

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

    The neuron fires on technical or procedural statements that name an agent (e.g. “engineers,” “designers,” “physician,” “testers”) followed by an action (often with “to,” “can,” or “will”), i.e. agent-verb constructions describing who does what.

    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
     постоянно
    -1.00
     politika
    -0.98
     reivindic
    -0.94
     уже
    -0.91
     тема
    -0.90
     agradec
    -0.88
     esbo
    -0.86
    тивно
    -0.85
     arşivlendi
    -0.84
    というわけで
    -0.84
    POSITIVE LOGITS
    IsNot
    1.08
     focuses
    1.02
     wieś
    1.02
     able
    1.00
     basso
    0.94
    you
    0.93
     hopes
    0.93
     Pontific
    0.93
    now
    0.91
     замет
    0.91
    Activations Density 0.077%

    No Known Activations