© 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. 16522
    Prev
    Next
    INDEX
    Explanations

    programming code getters

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

    The neuron fires on standalone numeric literals (integer tokens) in the code.

    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
    i
    -2.31
    焄
    -2.22
    tifies
    -2.03
     ändå
    -1.98
    }
    -1.97
    s
    -1.91
    Terima
    -1.78
    this
    -1.74
    But
    -1.73
    Semoga
    -1.72
    POSITIVE LOGITS
     pozwala
    2.00
    '
    1.86
    を利用
    1.85
    
    1.73
    tC
    1.73
     duże
    1.73
     hábit
    1.70
    ENES
    1.70
    kti
    1.68
    fion
    1.65
    Activations Density 0.007%

    No Known Activations