© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58206
    Prev
    Next
    INDEX
    Explanations

    traditional food and terms

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

    The neuron fires strongly on German‐language terms and names (foods, places, styles, etc.), i.e. words of German origin.

    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
     schnee
    -1.10
     Grünen
    -1.05
     Schloß
    -0.96
     Schrauben
    -0.95
     gewi
    -0.95
     köln
    -0.93
     jugend
    -0.92
     Jüng
    -0.92
     feuer
    -0.91
     Götter
    -0.90
    POSITIVE LOGITS
     traditional
    1.45
     authentic
    1.36
    Traditional
    1.33
     тради
    1.31
     Traditional
    1.22
     traditionellen
    1.21
    traditional
    1.13
     folklore
    1.05
     Authentic
    1.02
     traditionally
    1.01
    Activations Density 0.015%

    No Known Activations