© 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. 83604
    Prev
    Next
    INDEX
    Explanations

    intra, extra, peri prefixes

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

    The neuron fires on multi-morpheme medical terms built from Latin prefixes and combining forms (e.g. intra-, peri-/percutaneous, sub-, transtubular), marking the boundaries of complex anatomical or procedural vocabulary.

    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
    があり
    -1.23
    <bos>
    -0.99
    などは
    -0.94
    を持つ
    -0.93
    を
    -0.92
    などの
    -0.90
     herido
    -0.90
     nieruchomości
    -0.90
    もあり
    -0.90
    があるので
    -0.89
    POSITIVE LOGITS
    為に
    1.03
    の準備
    0.90
     року
    0.85
     Libertadores
    0.83
    ところに
    0.81
    に使用
    0.81
     Oll
    0.79
    θεν
    0.79
    する方法
    0.79
    choice
    0.79
    Activations Density 0.157%

    No Known Activations