© 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. 22808
    Prev
    Next
    INDEX
    Explanations

    things in common

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

    The neuron fires on the phrase “in common,” i.e. markers of shared/common attributes between things.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     and
    -2.56
     in
    -2.06
     lion
    -2.02
    </u>
    -2.00
     heart
    -1.84
    </i>
    -1.77
     joyas
    -1.71
    But
    -1.70
     self
    -1.70
     part
    -1.70
    POSITIVE LOGITS
    s
    2.17
    鲵
    1.98
    n
    1.97
     uan
    1.94
    ou
    1.84
    breviations
    1.83
    am
    1.83
     -¿
    1.81
    quelize
    1.78
     deere
    1.77
    Activations Density 0.011%

    No Known Activations