© 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. 9808
    Prev
    Next
    INDEX
    Explanations

    companies, teams, and empires in decline

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

    This neuron fires on tokens that are named-entity elements—proper names, organizations, and numeric data.

    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
    rule
    -0.95
    ξω
    -0.93
    leave
    -0.92
    を高
    -0.90
    ינוך
    -0.89
    expand
    -0.88
    龇
    -0.87
    adlo
    -0.86
     religieuses
    -0.86
    が高
    -0.85
    POSITIVE LOGITS
     struggling
    1.19
     asisti
    1.02
     revival
    1.02
     failed
    1.00
     failing
    0.99
     deteriorated
    0.95
     langu
    0.94
     bankruptcy
    0.94
    failing
    0.94
     decline
    0.93
    Activations Density 0.145%

    No Known Activations