© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2610
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

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

    The neuron strongly activates on numeric and punctuation tokens in code and license boilerplate—especially version numbers, years, and the dot separators in module paths and license headers.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     recevrez
    -0.82
    OMBIA
    -0.81
    試し
    -0.76
     aura
    -0.76
     actively
    -0.75
    Bris
    -0.75
    읍
    -0.73
     Estimates
    -0.73
     становника
    -0.72
     повы
    -0.70
    POSITIVE LOGITS
    NameInMap
    0.96
     alie
    0.85
     パターン
    0.85
    HasBeenSet
    0.84
    好像
    0.84
    
    0.83
    SDK
    0.83
     SDK
    0.83
    brities
    0.81
    仍然
    0.80
    Activations Density 0.014%

    No Known Activations