© 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. 76239
    Prev
    Next
    INDEX
    Explanations

    koz, kuz, coz, z

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

    The neuron selectively activates on tokens containing the letter “z” (often in name fragments like “Kuz,” “hiz,” “Koz,” or the digraph “zh”).

    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
    ğmen
    -0.72
    脚注
    -0.71
     dáng
    -0.71
     Energia
    -0.69
    ⦆
    -0.69
     unsound
    -0.69
    nota
    -0.67
    PT
    -0.67
     ombro
    -0.67
     weaponry
    -0.66
    POSITIVE LOGITS
     míst
    0.77
    ferential
    0.74
     ilość
    0.74
     Koz
    0.72
     ELSE
    0.71
     Ministerial
    0.70
     halls
    0.70
    QZ
    0.69
    arthur
    0.68
    conium
    0.68
    Activations Density 0.016%

    No Known Activations