© 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. 10-GEMMASCOPE-RES-131K
    4. 105873
    Prev
    Next
    INDEX
    Explanations

    Tulum, Cairns, parasites, places

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

    This neuron detects geographical locations and scientific terms related to Central America, particularly the Yucatan Peninsula and associated organisms.

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

    The neuron is tuned to spotting Latinized scientific names (e.g. genus–species terms in taxonomy).

    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
     Inglés
    -1.40
    den
    -1.34
    ton
    -1.32
     Técnico
    -1.31
    ITY
    -1.30
    艫
    -1.29
    sion
    -1.28
    erals
    -1.27
     Ilustra
    -1.27
    af
    -1.24
    POSITIVE LOGITS
    </strong>
    1.62
     kürzlich
    1.55
     bestens
    1.40
    diferentes
    1.39
    soo
    1.38
     mite
    1.38
     siente
    1.34
     sólida
    1.34
     angem
    1.33
    考え方
    1.33
    Activations Density 0.024%

    No Known Activations