© 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. 60592
    Prev
    Next
    INDEX
    Explanations

    names starting with A or Ar

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

    The neuron fires on author name segments—especially single-letter initials and capitalized surnames—in academic paper author lists.

    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
    require
    -0.75
    сматри
    -0.73
    setTitle
    -0.72
    啮
    -0.72
    名を
    -0.69
    abestanden
    -0.69
     conférence
    -0.69
     iaitu
    -0.68
     GARDEN
    -0.68
     reproductor
    -0.68
    POSITIVE LOGITS
    Referencias
    0.89
     doomed
    0.79
    Seu
    0.77
    Meu
    0.77
    >>;
    0.77
    csharp
    0.74
    buje
    0.74
     numerosi
    0.74
    SDG
    0.73
    証券
    0.73
    Activations Density 0.098%

    No Known Activations