© 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. 4313
    Prev
    Next
    INDEX
    Explanations

    Johnny Cage, Dumb Starbucks

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

    The neuron strongly fires on bits of copyright and licensing boilerplate (e.g. “rights reserved,” copyright notices, redistribution conditions).

    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
    ræ
    -0.77
     Orb
    -0.76
    ┃
    -0.74
    onatos
    -0.73
     VMs
    -0.71
    tsy
    -0.71
     Prefecture
    -0.70
    원
    -0.70
     Treat
    -0.69
    ピーク
    -0.69
    POSITIVE LOGITS
    Newman
    0.85
    ckeys
    0.84
     Newman
    0.83
     Rosales
    0.82
    &
    0.74
    ◔
    0.73
     bardziej
    0.72
     Genoa
    0.72
    llung
    0.71
    cobs
    0.69
    Activations Density 0.004%

    No Known Activations