© 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. 24036
    Prev
    Next
    INDEX
    Explanations

    eukaryotic cells

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

    The word "eukaryotic" in scientific or academic contexts.

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

    The neuron selectively activates on the phrase “The New Yorker.”

    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
     asomb
    -2.48
    m
    -2.31
    멱
    -2.25
    䊐
    -2.25
    巨大的
    -2.23
    常见的
    -2.17
    oinette
    -2.17
     イラストレーション
    -2.16
    另一种
    -2.16
    tisgarh
    -2.13
    POSITIVE LOGITS
    1
    2.70
    ,”
    2.70
     ‘
    2.53
    在他
    2.44
     Their
    2.36
     They
    2.33
    5
    2.20
    Their
    2.13
    2
    2.13
    us
    2.08
    Activations Density 0.002%

    No Known Activations