© 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. 90518
    Prev
    Next
    INDEX
    Explanations

    name attributes or assignments

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

    This neuron fires on occurrences of “name” (in any casing, e.g. Name or name) when used as an attribute or parameter key.

    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
     never
    -0.92
    ensioni
    -0.86
     patiently
    -0.84
    чам
    -0.83
     wouldn
    -0.81
    ഢ
    -0.81
     didn
    -0.81
     lefs
    -0.79
    aturen
    -0.78
     there
    -0.78
    POSITIVE LOGITS
     "
    1.26
     “
    1.23
    ldquo
    0.83
     berbeda
    0.81
     wieku
    0.79
    logía
    0.77
     разные
    0.77
    Unique
    0.74
     Newspaper
    0.74
    different
    0.73
    Activations Density 0.003%

    No Known Activations