© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66181
    Prev
    Next
    INDEX
    Explanations

    aliases and scientific names

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

    last names of people, particularly in combination with dates or URLs.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to tokens beginning with the letter sequence “ba” (for example in names like Bailey, Bali, Bahadur, or chemical terms like Barium).

    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
    ソナ
    -0.83
     attaches
    -0.82
     осо
    -0.81
    zości
    -0.80
     incline
    -0.75
    真っ
    -0.75
     cause
    -0.75
    tingu
    -0.73
     Accu
    -0.71
     brid
    -0.71
    POSITIVE LOGITS
     manifesta
    0.91
    空格
    0.79
     servire
    0.77
     Viewer
    0.76
    bedienung
    0.76
    ᆺ
    0.75
     organisme
    0.74
    couraged
    0.74
     navigator
    0.72
    យ
    0.71
    Activations Density 0.038%

    No Known Activations