© 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. 32794
    Prev
    Next
    INDEX
    Explanations

    new column name

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

    This neuron fires on tokens that occur inside code-level argument lists (e.g. parameters in function/method signatures or arguments inside call parentheses/braces).

    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
     Pekan
    -1.05
     predecess
    -1.02
    Более
    -1.02
     Ayam
    -0.96
     berlina
    -0.95
     Jambi
    -0.95
     lapin
    -0.93
     Sumatera
    -0.93
     tuturor
    -0.93
    美味しく
    -0.93
    POSITIVE LOGITS
    entamiento
    1.24
     new
    1.17
     neuen
    1.10
     אתה
    1.01
     nieuwe
    0.98
     descrito
    0.96
     nuevas
    0.95
     nowej
    0.94
     chłod
    0.94
     desired
    0.94
    Activations Density 0.015%

    No Known Activations