© 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. 34-GEMMASCOPE-RES-131K
    7. 56715
    Prev
    Next
    INDEX
    Explanations

    normal, routine, reversible, known, partial, major

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

    The neuron fires on technical report–style keywords that introduce or describe study parameters, categories, or measured quantities (e.g. “prevalence,” “incidence,” “selective,” “routine,” “normal,” “total,” “partial”).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Fotografía
    -0.93
     irgend
    -0.93
    Commentaires
    -0.88
    opatho
    -0.88
    Flashback
    -0.87
    女人的
    -0.84
     pensó
    -0.82
    Silly
    -0.82
    好像是
    -0.81
    Évaluation
    -0.81
    POSITIVE LOGITS
     such
    1.37
     melakukannya
    1.14
     ones
    1.11
     extenso
    1.04
     тако
    1.04
     ilyen
    1.03
     kuat
    1.02
     rupiah
    0.96
     Jpa
    0.95
     solchen
    0.90
    Activations Density 0.456%

    No Known Activations