© 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. 84502
    Prev
    Next
    INDEX
    Explanations

    efficient breeding systems

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

    information related to organizational entities, particularly in Indonesia, including institutional names, positions, and formal structures.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires strongly on capitalized tokens that are part of formal proper names—especially organization names, official titles, and other named‐entity components.

    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
     Kementerian
    -0.95
     raso
    -0.91
     Menteri
    -0.90
     siti
    -0.89
     orec
    -0.87
     Paese
    -0.86
     filma
    -0.86
     hial
    -0.86
     Cæ
    -0.85
     panela
    -0.85
    POSITIVE LOGITS
     motiv
    0.84
     team
    0.84
     ugy
    0.79
    
    0.79
     Alumni
    0.77
    否则
    0.77
     Task
    0.77
     Hum
    0.77
    ø
    0.77
     BB
    0.76
    Activations Density 0.002%

    No Known Activations