© 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. 34-GEMMASCOPE-RES-131K
    7. 34712
    Prev
    Next
    INDEX
    Explanations

    Cypress Park, Interleukin

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

    years or dates in numerical format (like 2005, 2020, 2012, etc.).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on uppercase sports‐event headings (e.g. “2005 WNBA Playoffs”), i.e. section titles for sporting competitions.

    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
    献
    -0.87
     adonan
    -0.82
    鬨
    -0.79
    PUS
    -0.78
    inoc
    -0.78
     hoops
    -0.77
    endront
    -0.77
     tourism
    -0.76
     divisions
    -0.75
     техні
    -0.74
    POSITIVE LOGITS
     Houston
    0.87
    Atlanta
    0.81
     Atlanta
    0.79
    NameInMap
    0.76
    ).*
    0.76
     TLR
    0.74
    ">*
    0.72
    celery
    0.69
    wehr
    0.67
     ağ
    0.67
    Activations Density 0.028%

    No Known Activations