© 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. 110926
    Prev
    Next
    INDEX
    Explanations

    park land reservation

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

    This neuron responds to numerical tokens—especially years and other numbers—wherever they appear in the text.

    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
     Einheit
    -0.75
     domác
    -0.72
    ద్య
    -0.71
    ibir
    -0.69
    ላ
    -0.68
    endeu
    -0.68
     zesta
    -0.67
     agricoles
    -0.67
    ({},
    -0.66
    archer
    -0.66
    POSITIVE LOGITS
     reservation
    1.16
     Reservation
    1.02
    reservations
    1.02
     dedication
    0.97
     reserved
    0.97
     reservations
    0.96
     dedica
    0.96
    Reservation
    0.95
     dedic
    0.94
    reservation
    0.94
    Activations Density 0.018%

    No Known Activations