© 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. 22-GEMMASCOPE-RES-131K
    7. 130675
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on mentions of Irish identity or Ireland (e.g. “Irish,” “Ireland,” and related geographic/national references).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Irish affiliation, nationality, or cultural terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ↵
    -3.11
     fabricación
    -2.42
    C
    -2.41
    D
    -2.39
    A
    -2.38
     grossen
    -2.33
    E
    -2.31
     страны
    -2.19
    少々
    -2.19
     serán
    -2.17
    POSITIVE LOGITS
    🌸
    2.41
     resides
    2.31
    }
    2.27
     contends
    2.25
     retains
    2.20
     succeeds
    2.19
     exercí
    2.17
    TextInputLayout
    2.13
    👀
    2.13
    💕
    2.09
    Activations Density 0.009%

    No Known Activations