© 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. 68873
    Prev
    Next
    INDEX
    Explanations

    parentage and breeding

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

    terms related to animal breeding and genetics, particularly focusing on parents, offspring, and breeding lineage.

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

    The neuron activates on numeric measurement tokens—e.g. quantities, statistics, and other numbers (especially decimals).

    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
     discrepan
    -1.61
    呖
    -1.46
    R
    -1.45
     leal
    -1.43
     economico
    -1.41
    ização
    -1.39
    ホームページ
    -1.39
    谂
    -1.38
     involunt
    -1.38
     confr
    -1.38
    POSITIVE LOGITS
     that
    1.66
     the
    1.43
    '
    1.41
     Crear
    1.34
    ;
    1.28
     geliefert
    1.23
    でて
    1.17
     zowel
    1.16
     Mostrar
    1.16
    的模样
    1.14
    Activations Density 0.015%

    No Known Activations