© 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. 2164
    Prev
    Next
    INDEX
    Explanations

    major entities and rankings

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

    The neuron fires on occurrences of the phrase “Big Four” (and analogous “four major” groupings) naming the top quartet in contexts like broadcast networks or sports leagues.

    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
    たたみ
    -0.88
    了一眼
    -0.78
    ковая
    -0.77
     sangat
    -0.76
     feats
    -0.76
     儿
    -0.75
     objects
    -0.75
    শে
    -0.74
    ному
    -0.74
    Divider
    -0.73
    POSITIVE LOGITS
     major
    3.95
    major
    3.14
    Major
    2.52
    MAJOR
    2.31
     Major
    2.14
     MAJOR
    2.03
    各大
    1.99
    主要
    1.93
     majors
    1.80
     mainstream
    1.68
    Activations Density 0.140%

    No Known Activations