© 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. 87205
    Prev
    Next
    INDEX
    Explanations

    Zach, Zah, DOH, захо

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

    This neuron responds to occurrences of the character sequence “zah” (in any context).

    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
    eneration
    -0.79
     Fortress
    -0.78
     Afghans
    -0.77
    lyt
    -0.75
    itori
    -0.75
    kaper
    -0.75
    יק
    -0.74
     FIGHT
    -0.73
    łoni
    -0.73
     Acest
    -0.72
    POSITIVE LOGITS
    uc
    0.70
    ộm
    0.68
    čke
    0.66
     rapides
    0.66
    ྱ
    0.65
    三星
    0.65
    acknowledge
    0.65
    屯
    0.65
    anthemum
    0.64
    Actions
    0.64
    Activations Density 0.039%

    No Known Activations