© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58708
    Prev
    Next
    INDEX
    Explanations

    adding elements to lists

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

    The neuron detects literal empty list constructions (i.e. occurrences of “[]”).

    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
    setFont
    -0.82
    subaru
    -0.81
     Sister
    -0.81
     amarillas
    -0.80
    NSArray
    -0.79
     guy
    -0.78
    lrrr
    -0.78
     desconocido
    -0.75
     should
    -0.75
     ногтей
    -0.75
    POSITIVE LOGITS
     for
    1.05
     добавить
    0.96
    push
    0.96
     zprá
    0.91
    Доба
    0.89
    PUSH
    0.89
    添加
    0.86
    cians
    0.86
     добав
    0.84
    wijl
    0.83
    Activations Density 0.011%

    No Known Activations