© 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. 127599
    Prev
    Next
    INDEX
    Explanations

    words followed by specific punctuation or prepositions

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

    The neuron fires on longer, morphologically complex content words—especially inflected verb forms like past participles (-ed) and gerunds (-ing).

    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
     on
    -1.75
     then
    -1.43
     this
    -1.28
     its
    -1.25
     CITIES
    -1.16
     especializado
    -1.09
    غير
    -1.08
     by
    -1.08
     RECOMM
    -1.08
     boules
    -1.07
    POSITIVE LOGITS
     élégante
    1.41
     blessé
    1.31
    rierung
    1.30
     Fantastic
    1.27
     cinco
    1.27
     большинстве
    1.27
    tamment
    1.27
     частности
    1.26
     nejs
    1.26
    teurs
    1.25
    Activations Density 0.241%

    No Known Activations