© 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. 60752
    Prev
    Next
    INDEX
    Explanations

    Online arguments and backlash

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

    The neuron strongly activates on celebrity‐gossip headline phrases—especially proper names of pop stars or entertainers in article titles.

    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
     собе
    -0.96
    toolTip
    -0.93
     AWESOME
    -0.93
    Ārējās
    -0.92
     quí
    -0.89
     visitar
    -0.87
    明年
    -0.86
    теру
    -0.85
     :)
    -0.84
    扫描
    -0.84
    POSITIVE LOGITS
     receipts
    1.28
     Receipts
    1.28
     screenshots
    1.23
     backlash
    1.20
     allegations
    1.15
    Shade
    1.14
    clap
    1.12
     Shade
    1.09
     Keyboard
    1.05
    shade
    1.02
    Activations Density 0.051%

    No Known Activations