© 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. 10-GEMMASCOPE-RES-131K
    7. 39353
    Prev
    Next
    INDEX
    Explanations

    coast, coastline, coastal cities and towns

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

    This neuron activates on words and fragments related to coasts (e.g., coastal, coastline, coast).

    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
     жовтня
    -1.86
     пользователем
    -1.84
     серпня
    -1.82
    してました
    -1.79
     Penyakit
    -1.74
     spaced
    -1.70
     configurar
    -1.68
    When
    -1.68
     AGUA
    -1.67
    になってしまう
    -1.66
    POSITIVE LOGITS
     '
    2.80
    ↵
    2.63
    -
    2.03
     bisher
    1.97
     \
    1.96
     You
    1.89
     enorme
    1.88
     neue
    1.87
    ti
    1.84
     nieuwe
    1.83
    Activations Density 0.018%

    No Known Activations