© 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. 95732
    Prev
    Next
    INDEX
    Explanations

    errors and failures

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

    The neuron fires on numeric literals (sequences of digits) 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
    Conclusão
    -0.99
    Outras
    -0.97
    ՚
    -0.92
     maioria
    -0.91
    ↵↵
    -0.91
    meisters
    -0.91
    fgaben
    -0.90
    opardy
    -0.90
    CloseOperation
    -0.87
    uno
    -0.87
    POSITIVE LOGITS
     poleg
    1.03
    vão
    0.99
    剧照
    0.96
    toThrow
    0.96
    りましたが
    0.94
    きましたが
    0.93
     Хи
    0.93
    ⎙
    0.92
    𝟹
    0.92
     ſer
    0.92
    Activations Density 0.001%

    No Known Activations