© 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. 65916
    Prev
    Next
    INDEX
    Explanations

    names preceded by "By"

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

    The neuron activates on byline tokens—that is, bits of author-name lines (e.g. “By,” personal names, and similar header credits).

    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
    雜誌
    -0.93
     featuring
    -0.89
    userDetails
    -0.89
     famí
    -0.88
     achieved
    -0.82
    彼が
    -0.82
    Karakter
    -0.81
     artículos
    -0.81
     features
    -0.80
    產業
    -0.79
    POSITIVE LOGITS
    NaOH
    1.03
    PRNewswire
    1.00
    杉
    0.91
    titem
    0.88
    voa
    0.85
    GeneratedMessage
    0.84
    弈
    0.83
    Reuters
    0.82
    djangoproject
    0.82
     Passover
    0.82
    Activations Density 0.024%

    No Known Activations