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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68908
    Prev
    Next
    INDEX
    Explanations

    programming keywords and symbols

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

    This neuron activates on numeric literals (integer constants) in code.

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

    No Comments

    Negative Logits
     "
    -1.09
    adă
    -0.95
     zusätzlich
    -0.92
     贴
    -0.92
     increase
    -0.90
    ];
    -0.88
     дешевле
    -0.88
     deinen
    -0.86
     to
    -0.85
     täglich
    -0.85
    POSITIVE LOGITS
     äta
    1.02
     each
    0.93
     jätte
    0.92
    𝔾
    0.92
     vivre
    0.91
     Să
    0.91
     передний
    0.89
     mâ
    0.89
     réfugi
    0.89
     ouest
    0.88
    Activations Density 0.017%

    No Known Activations