© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67941
    Prev
    Next
    INDEX
    Explanations

    Chesapeake Bay and names with Ri

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

    The neuron specifically activates on the place name “Chesapeake.”

    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
    I
    -2.86
     THE
    -2.77
     When
    -2.59
    \
    -2.58
     WHAT
    -2.56
    м
    -2.53
     porsi
    -2.50
     sebaik
    -2.50
     Would
    -2.45
     exceptionnel
    -2.41
    POSITIVE LOGITS
    '
    3.08
    璈
    2.53
     was
    2.05
    ῞
    2.05
    而去
    2.02
    ांकि
    2.00
    之内
    2.00
    ’
    1.99
     becau
    1.98
    同上
    1.95
    Activations Density 0.013%

    No Known Activations