© 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. 22-GEMMASCOPE-RES-131K
    7. 24980
    Prev
    Next
    INDEX
    Explanations

    Big Bang Theory

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

    The neuron flags isolated named‐entity tokens—especially acronyms, brand names, and other proper‐noun labels.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     İstanbul
    -0.98
     garan
    -0.98
     dinoss
    -0.93
     variabel
    -0.93
     elektri
    -0.93
     København
    -0.93
     seks
    -0.92
     kark
    -0.92
     kome
    -0.92
     gitar
    -0.91
    POSITIVE LOGITS
    1.05
    </b>
    1.04
     while
    1.01
    </i>
    1.00
     promoting
    0.98
     with
    0.97
     beschäf
    0.97
     kebersihan
    0.96
    ̡
    0.93
     мед
    0.91
    Activations Density 0.000%
    No Known Activations