© 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. 106674
    Prev
    Next
    INDEX
    Explanations

    code get accessors

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

    The neuron fires on tokens inside programming method or function declarations—especially getter names (e.g. “get”, “getId”, “getName”) and similar method‐signature keywords.

    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
     CONTRIBUTION
    -1.02
     maravilh
    -1.01
     suporte
    -0.99
     COMMERCE
    -0.98
     Erkenntnisse
    -0.95
    鷥
    -0.95
    
    -0.95
     acabamento
    -0.94
     ARTISTS
    -0.94
     rigu
    -0.93
    POSITIVE LOGITS
     get
    1.62
     gets
    1.32
     at
    1.12
     with
    1.11
     as
    1.05
     ребенку
    1.03
     takes
    0.95
     while
    0.94
     although
    0.92
     in
    0.91
    Activations Density 0.002%

    No Known Activations