© 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. 62665
    Prev
    Next
    INDEX
    Explanations

    plotting commands and git operations

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

    The neuron fires on the “.” in object‐method calls (i.e. the attribute‐access dot preceding a method name).

    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
     to
    -0.94
     Until
    -0.88
     set
    -0.87
     mitte
    -0.87
     gesundheit
    -0.84
     Equi
    -0.83
     without
    -0.81
    taya
    -0.81
    licit
    -0.80
     Jerman
    -0.80
    POSITIVE LOGITS
    scatter
    0.91
    ][:
    0.90
    `.
    0.88
    幔
    0.88
    มัน
    0.88
     ("\
    0.88
     biet
    0.88
    ashir
    0.87
    大大
    0.87
    黏
    0.86
    Activations Density 0.002%

    No Known Activations