© 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. 58394
    Prev
    Next
    INDEX
    Explanations

    country names and codes

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

    The neuron fires on country names (e.g. “United States,” “Albania,” “Algeria,” etc.) in data structures.

    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
    thodoxy
    -1.10
     this
    -1.09
    cinct
    -0.96
     zależ
    -0.95
    のこ
    -0.95
    kraine
    -0.95
     taskId
    -0.94
     tools
    -0.92
    crete
    -0.91
    _{{\
    -0.91
    POSITIVE LOGITS
    着丈
    1.02
    Slovakia
    1.02
    日常生活
    1.00
    销毁
    0.96
    Referencer
    0.96
     réfrigérateur
    0.96
    Oby
    0.94
    ちなみに
    0.93
     pleasantly
    0.92
    hnte
    0.92
    Activations Density 0.016%

    No Known Activations