© 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. 98897
    Prev
    Next
    INDEX
    Explanations

    review, overview, update, introduction

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

    The neuron fires on title‐heading words that label the paper as a review/overview/update (e.g. “review,” “overview,” “update”).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     учитывать
    -1.36
     épisode
    -1.35
    inspira
    -1.34
     contribue
    -1.26
     információ
    -1.25
     fokus
    -1.23
    Should
    -1.22
     eventuell
    -1.20
     заменить
    -1.19
    媗
    -1.19
    POSITIVE LOGITS
     now
    1.51
     more
    1.46
     mesmas
    1.39
     less
    1.36
    </em>
    1.36
    Aktualisiert
    1.29
    "
    1.27
     new
    1.23
    .”
    1.22
     what
    1.20
    Activations Density 0.246%

    No Known Activations