© 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. 19427
    Prev
    Next
    INDEX
    Explanations

    relapse, Triton, Dory

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

    The neuron detects occurrences of the word “Triton.”

    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
    as
    -2.83
    r
    -2.70
    v
    -2.56
     vorigen
    -2.48
     nuovi
    -2.48
    an
    -2.48
    ):
    -2.45
     alamy
    -2.42
    のは
    -2.42
    li
    -2.42
    POSITIVE LOGITS
     tomado
    2.39
     spooky
    2.38
     simmer
    2.38
     favoritas
    2.33
    ?’
    2.33
     gastos
    2.30
     gustado
    2.27
     dinosaur
    2.23
     últimas
    2.22
    BagLayout
    2.22
    Activations Density 0.058%

    No Known Activations