© 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. 83932
    Prev
    Next
    INDEX
    Explanations

    show or shows

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

    The neuron responds to various conjugations or cognates of the verb “show” (e.g. показать, mostrar/mostra/mostrando, muestre, Zeig- in Zeigler).

    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
    }
    -2.36
     In
    -2.31
    姈
    -2.28
     applause
    -2.19
     That
    -2.11
    $
    -2.00
    ୌ
    -1.95
    ０
    -1.90
     kuin
    -1.88
     dalam
    -1.87
    POSITIVE LOGITS
    </em>
    2.66
    鲧
    2.36
    蹓
    2.22
    ising
    2.20
    身后的
    2.16
     relacionadas
    2.14
    bandicam
    2.13
    </h4>
    2.13
    疍
    2.13
    ੴ
    2.09
    Activations Density 0.005%

    No Known Activations