© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38683
    Prev
    Next
    INDEX
    Explanations

    names starting with nich

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

    The neuron is specialized to detect the surname variants “Nichols” and “Nicholson.”

    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
     verschill
    -2.52
     doubtless
    -2.39
    鹚
    -2.27
    queles
    -2.27
     Dritte
    -2.22
    ebbe
    -2.19
    枼
    -2.19
     otras
    -2.19
    中期
    -2.17
     really
    -2.16
    POSITIVE LOGITS
    medriver
    3.09
    </h3>
    2.67
     
    2.66
    2
    2.55
    鉿
    2.50
    9
    2.44
     यदि
    2.42
    3
    2.39
    になりました
    2.38
     ジップ
    2.30
    Activations Density 0.003%

    No Known Activations