© 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. 22-GEMMASCOPE-RES-131K
    7. 64265
    Prev
    Next
    INDEX
    Explanations

    programming and translation references

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

    This neuron fires on standalone numeric list markers (e.g. chapter‐ or section numbers like “1.”, “2.”, “3.”) in both Chinese and English formatted lists.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     that
    -1.51
     sebagai
    -1.50
    Another
    -1.49
     However
    -1.45
    This
    -1.45
     beserta
    -1.41
    想必
    -1.36
    ässer
    -1.36
    ffine
    -1.34
    他没有
    -1.34
    POSITIVE LOGITS
    excellents
    1.55
     vinculados
    1.48
     komplet
    1.48
     Heilige
    1.46
     únicos
    1.46
     condição
    1.45
     flexível
    1.45
     destinados
    1.45
     klassi
    1.42
     enviados
    1.42
    Activations Density 0.004%

    No Known Activations