© 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. 50449
    Prev
    Next
    INDEX
    Explanations

    names ending in -utz, -itz, -itzler

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

    This neuron activates on words containing the letter sequence “tz,” especially proper names or terms (e.g. “Putz,” “Lutz,” “Spitz,” “Metz”).

    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
     和
    -0.79
     does
    -0.78
    DF
    -0.77
    RequestQueue
    -0.73
     весь
    -0.73
     expectativas
    -0.73
     systems
    -0.72
     dozens
    -0.71
    zade
    -0.71
    <0x9E>
    -0.70
    POSITIVE LOGITS
    elfde
    0.89
     Intelligen
    0.87
     unsus
    0.82
    chach
    0.81
    暌
    0.80
    Spray
    0.79
     Shaman
    0.78
     Psychiatric
    0.78
     zei
    0.77
     Pius
    0.77
    Activations Density 0.023%

    No Known Activations