© 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. 38588
    Prev
    Next
    INDEX
    Explanations

    actions followed by objects

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

    The neuron fires on verbs in their past-tense or past-participial form.

    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
     to
    -1.52
    ",
    -1.27
     була
    -1.23
    président
    -1.21
    ьев
    -1.20
    quelize
    -1.19
    之为
    -1.18
    ,”
    -1.17
     ameryka
    -1.16
    -1.16
    POSITIVE LOGITS
    dersfield
    1.34
    </em>
    1.34
    лении
    1.31
     ferrovia
    1.28
     compris
    1.28
    メニューは
    1.27
     namor
    1.27
     schwar
    1.27
     jesteśmy
    1.27
    他们在
    1.25
    Activations Density 0.007%
    No Known Activations