© 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. 10-GEMMASCOPE-RES-131K
    4. 9949
    Prev
    Next
    INDEX
    Explanations

    urban dwellers

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

    This neuron detects the names of formal organizations or political group entities (e.g. multiword proper‐noun titles like “National Front,” “Council,” “Party,” 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_10/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
     любого
    -1.08
    Ār
    -1.04
    Дорогие
    -0.97
    Тарихы
    -0.96
     harap
    -0.96
     menn
    -0.94
    Уважаемые
    -0.92
     zina
    -0.91
     ܐ
    -0.91
    Lä
    -0.91
    POSITIVE LOGITS
     yesterday
    1.16
     these
    1.09
     назначения
    1.07
     éstos
    1.07
    ixels
    1.06
     Preisen
    1.05
     participar
    1.05
    icolo
    1.05
    hoenix
    1.03
    esticides
    1.02
    Activations Density 0.012%

    No Known Activations