© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98381
    Prev
    Next
    INDEX
    Explanations

    Scottish government and organizations

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

    The neuron fires on mentions of “Scottish” or other direct references to Scotland (e.g. Scottish Government, Scottish institutions, etc.).

    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
    "];
    -0.84
    ключение
    -0.77
    FormatException
    -0.75
    好看
    -0.74
    VL
    -0.74
    İZ
    -0.73
     ため
    -0.73
    Foundation
    -0.73
     noDo
    -0.73
    "};
    -0.73
    POSITIVE LOGITS
     Rite
    0.89
    lerinden
    0.75
     οπο
    0.75
    WAT
    0.74
    Asian
    0.74
     bacio
    0.73
    eky
    0.73
    anom
    0.72
    臨時
    0.72
    imply
    0.71
    Activations Density 0.024%

    No Known Activations