© 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. 57641
    Prev
    Next
    INDEX
    Explanations

    extinct species and genera

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

    The neuron detects words related to extinction, particularly the word "extinct" in taxonomic or scientific contexts.

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

    The neuron activates whenever it sees the proper noun “Boyd.”

    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
    拍了拍
    -2.59
    转头
    -2.48
    0
    -2.33
    iwisata
    -2.25
    ཋ
    -2.23
    蕺
    -2.23
    觏
    -2.23
    のほうが
    -2.22
    螣
    -2.19
    抬手
    -2.13
    POSITIVE LOGITS
    y
    3.44
    是
    3.02
    en
    3.00
    <td>
    2.69
    is
    2.67
     способом
    2.66
    x
    2.61
    on
    2.56
    er
    2.38
    te
    2.38
    Activations Density 0.003%

    No Known Activations