© 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. 73596
    Prev
    Next
    INDEX
    Explanations

    uma followed by ker

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

    The neuron activates on the character sequence “uma” (and its adjoining context) wherever it appears, especially inside proper names.

    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
     Permit
    -0.71
    ätä
    -0.70
    Permit
    -0.69
    zemu
    -0.68
     minimise
    -0.68
    Atk
    -0.66
    猜
    -0.66
    ългар
    -0.66
     permit
    -0.66
    VIDE
    -0.66
    POSITIVE LOGITS
    錯
    0.79
     pprint
    0.76
    Scene
    0.75
     نقد
    0.75
     Mother
    0.73
    види
    0.72
    퀘
    0.72
     questão
    0.72
     regalías
    0.71
     SCENE
    0.70
    Activations Density 0.025%

    No Known Activations