© 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. 38641
    Prev
    Next
    INDEX
    Explanations

    username or name fields

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

    The neuron is triggered by occurrences of the identifier “username” (e.g. code or schema fields named username).

    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
    </h4>
    -1.74
    縂
    -1.48
     kutu
    -1.47
     pirata
    -1.45
    飏
    -1.45
     also
    -1.44
     bulu
    -1.44
    </u>
    -1.40
     concorda
    -1.39
    莇
    -1.38
    POSITIVE LOGITS
    ଃ
    1.79
     邊
    1.66
    躋
    1.62
    甭
    1.55
    讫
    1.51
    ⎆
    1.51
    念头
    1.49
    实话
    1.48
    瑆
    1.48
    InputBorder
    1.46
    Activations Density 0.036%

    No Known Activations