© 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. 79387
    Prev
    Next
    INDEX
    Explanations

    concept formation and synthesis

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

    The neuron strongly responds to common high‐frequency function words (e.g. “the,” “and,” “to,” “of”), punctuation (commas, colons), and other grammatical scaffolding 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
     黄色
    -0.88
     Fra
    -0.85
     affich
    -0.84
    覗
    -0.82
    dokument
    -0.82
     Zhou
    -0.81
     komplett
    -0.81
     Chrom
    -0.81
     کرمان
    -0.81
    😱
    -0.81
    POSITIVE LOGITS
     synthesis
    1.77
     synthe
    1.54
     connections
    1.45
    Synthe
    1.44
     synthesize
    1.41
    synthesis
    1.32
     синте
    1.32
     Synthesis
    1.31
    synthe
    1.28
     linking
    1.24
    Activations Density 0.049%

    No Known Activations