© 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. 34-GEMMASCOPE-RES-131K
    7. 73559
    Prev
    Next
    INDEX
    Explanations

    names like Judith

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

    The neuron responds to name fragments beginning with “Ju” (e.g. Judi-, Judit-, Juárez-, Judith-).

    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
    稀
    -0.78
     druk
    -0.77
     tổ
    -0.74
    Pizza
    -0.74
    FromArgb
    -0.73
    ciation
    -0.73
    apie
    -0.71
     temptations
    -0.71
    manie
    -0.71
    CLU
    -0.70
    POSITIVE LOGITS
    ؔ
    0.73
     човек
    0.71
     作り方
    0.69
     дів
    0.69
     modified
    0.69
    zioso
    0.69
    idemia
    0.68
    tador
    0.66
    ánló
    0.66
     jump
    0.66
    Activations Density 0.026%

    No Known Activations