© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116484
    Prev
    Next
    INDEX
    Explanations

    names beginning with iz

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

    The neuron strongly activates on occurrences of the letter sequence “Iz,” especially when it appears as the prefix of a word.

    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
    ∭
    -0.80
     笔
    -0.75
     significa
    -0.72
    を含
    -0.70
    Proximity
    -0.70
     pare
    -0.69
    codes
    -0.69
    app
    -0.68
     childhood
    -0.68
    をはじめ
    -0.66
    POSITIVE LOGITS
    Iz
    0.97
    こんばんは
    0.85
     Iz
    0.83
    مرا
    0.82
     iz
    0.82
    Going
    0.80
     cyc
    0.78
    ＿＿
    0.77
     DbContext
    0.77
     geweest
    0.76
    Activations Density 0.013%

    No Known Activations