© 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. 70581
    Prev
    Next
    INDEX
    Explanations

    place origins

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

    The neuron strongly activates on words denoting specific places or spatial locations (e.g. locations, areas, facilities, place names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    cepatan
    -0.88
    autés
    -0.87
     συγ
    -0.83
    Surprised
    -0.82
    ⲧ
    -0.81
    jalankan
    -0.80
     enshrined
    -0.80
    หน้าน
    -0.77
     kommen
    -0.75
     delante
    -0.75
    POSITIVE LOGITS
     base
    0.99
    whence
    0.96
     откуда
    0.93
     Ausgang
    0.88
     launching
    0.88
     origines
    0.87
     whence
    0.86
     информации
    0.84
     starting
    0.82
    kheim
    0.81
    Activations Density 0.159%

    No Known Activations