© 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. 95439
    Prev
    Next
    INDEX
    Explanations

    has / have / are / were + word

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

    The neuron responds to technical terms that describe scientific or medical causal and mechanistic concepts (e.g. cause, agent, mechanism, pathogenesis, identified).

    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
     для
    -1.02
     только
    -0.98
    での
    -0.97
    で
    -0.95
    əsi
    -0.92
    により
    -0.86
     SIGNIFIC
    -0.85
     deras
    -0.85
     برای
    -0.84
    urations
    -0.84
    POSITIVE LOGITS
     itself
    1.07
     identified
    1.00
     אותו
    0.96
    是谁
    0.94
     one
    0.90
     mêmes
    0.88
     destruir
    0.87
     herself
    0.86
     it
    0.86
     mechanism
    0.85
    Activations Density 0.115%

    No Known Activations