© 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. 30148
    Prev
    Next
    INDEX
    Explanations

    Java, programming, Q&A

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

    The neuron specializes in spotting software package coordinates and version identifiers (e.g. “org.apache.commons.math.Function” and numeric version tokens).

    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
    搪
    -0.93
     Konsequ
    -0.79
     DOI
    -0.78
    tener
    -0.75
    actéristiques
    -0.75
     polisi
    -0.75
     incó
    -0.74
    VIRONMENT
    -0.73
     lørdag
    -0.71
     chickens
    -0.70
    POSITIVE LOGITS
     combustibles
    0.87
     vooral
    0.83
    缓冲
    0.83
     fussy
    0.81
     planen
    0.79
     comedor
    0.79
    いたら
    0.78
    تهى
    0.77
     reputable
    0.77
     Hobbit
    0.77
    Activations Density 0.007%

    No Known Activations