© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11541
    Prev
    Next
    INDEX
    Explanations

    Icelandic geography and related concepts

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

    The neuron activates primarily on named entities—proper nouns like people’s names, places, organizations, and other capitalized titles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⊔
    0.63
    袬
    0.62
    妩
    0.59
     আদ
    0.59
    Съ
    0.59
     Lebanon
    0.59
     Съ
    0.59
    گذاری
    0.59
    হিন্দু
    0.57
     باك
    0.57
    POSITIVE LOGITS
     Icelandic
    1.99
     Iceland
    1.88
    Iceland
    1.87
     Reykjav
    1.77
     Reykjavik
    1.71
    ð
    1.35
     आइसलैंड
    1.26
     Faroe
    1.25
     Bj
    1.23
     Þ
    1.20
    Activations Density 0.124%

    No Known Activations