© 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. 34-GEMMASCOPE-RES-131K
    7. 54219
    Prev
    Next
    INDEX
    Explanations

    cost effectiveness or regulatory probes

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

    The neuron fires strongly whenever the text contains the conjunction “or.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    彼此
    -0.86
     Verdun
    -0.78
     Thorpe
    -0.71
     Organis
    -0.71
    verhältnisse
    -0.70
     manoeu
    -0.70
    thora
    -0.69
     Searle
    -0.68
    Organis
    -0.68
     DRM
    -0.68
    POSITIVE LOGITS
    Broadcast
    1.04
     complain
    0.98
     broadcast
    0.96
     Complaints
    0.95
     complaints
    0.94
     children
    0.93
     complaint
    0.93
     Broadcast
    0.90
     regulator
    0.88
     broadcasters
    0.86
    Activations Density 0.010%

    No Known Activations