© 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. 10-GEMMASCOPE-RES-131K
    7. 72798
    Prev
    Next
    INDEX
    Explanations

    compar- prefix

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

    The neuron strongly activates on words containing the substring “compar” (e.g. compare, comparable, comparative, comparators).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    푣
    -2.70
     cornerstone
    -2.44
     consideramos
    -2.44
     We
    -2.39
     penggunaan
    -2.30
    ◍
    -2.23
    硖
    -2.23
     Anſ
    -2.23
    meiras
    -2.22
     collaboration
    -2.19
    POSITIVE LOGITS
    0
    3.48
    ”
    2.92
    ”،
    2.89
    ons
    2.77
    by
    2.58
    while
    2.56
    咴
    2.55
    6
    2.42
    Ⲉ
    2.39
    总是
    2.36
    Activations Density 0.005%

    No Known Activations