© 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. 83763
    Prev
    Next
    INDEX
    Explanations

    parts of names

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

    The neuron is highly activated by capitalized proper nouns—that is, names of people or places.

    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
    ting
    -0.83
    рую
    -0.81
    ters
    -0.76
    tering
    -0.75
     оси
    -0.72
    niew
    -0.71
    ney
    -0.71
    Ŗ
    -0.69
    ča
    -0.69
    ten
    -0.69
    POSITIVE LOGITS
    に伴
    0.80
    Tired
    0.78
    surgery
    0.75
    symp
    0.75
    appear
    0.74
    ifornia
    0.73
     stycz
    0.73
    ials
    0.73
    いい
    0.73
     miłości
    0.72
    Activations Density 0.043%

    No Known Activations