© 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. 29980
    Prev
    Next
    INDEX
    Explanations

    names and descriptive adverbs

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

    The neuron strongly activates on capitalized tokens (especially proper names) and numeric tokens (dates, counts, etc.), i.e. elements of named entities and numbers.

    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
     .....
    -1.13
     ....
    -1.02
    although
    -1.00
     agosto
    -0.96
     will
    -0.95
     as
    -0.93
    巿
    -0.92
     informa
    -0.91
     F
    -0.90
    .......
    -0.89
    POSITIVE LOGITS
     delightfully
    1.32
     beautifully
    1.30
     místo
    1.27
     deliciously
    1.24
     hilfre
    1.22
     powerfully
    1.21
     wonderfully
    1.17
     vantagem
    1.17
    냑
    1.14
     vastly
    1.13
    Activations Density 0.029%

    No Known Activations