© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103337
    Prev
    Next
    INDEX
    Explanations

    immunodeficiency virus; irreverent

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

    proper names and acronyms.

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

    The neuron specifically activates on occurrences of the proper name “Myles.”

    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
    接下来的
    -2.64
     estadounid
    -2.53
    t
    -2.44
    .
    -2.41
    ーズン
    -2.30
    埸
    -2.28
     вернулся
    -2.27
     建物
    -2.27
     him
    -2.23
     treasured
    -2.22
    POSITIVE LOGITS
    闥
    2.59
    เกง
    2.53
    椅子
    2.50
    磲
    2.27
     وأ
    2.25
    ，“
    2.25
    </h5>
    2.23
    ☫
    2.22
     sont
    2.22
    2.22
    Activations Density 0.018%

    No Known Activations