© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2530
    Prev
    Next
    INDEX
    Explanations

    Colin, Collins, Kaepernick

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

    The neuron detects import statements referencing Python’s “collections” module.

    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
     Ramsay
    -0.83
    빗
    -0.81
    三位
    -0.79
    mainwindow
    -0.78
     polé
    -0.77
     confuso
    -0.76
    ניתן
    -0.73
     Bento
    -0.72
    vų
    -0.72
    entait
    -0.70
    POSITIVE LOGITS
     оста
    0.84
    mj
    0.79
     ELF
    0.78
     rzeczy
    0.74
    Singleton
    0.73
     ClassNotFound
    0.73
    ckett
    0.73
     exceedingly
    0.72
    khi
    0.72
    Indeed
    0.72
    Activations Density 0.007%

    No Known Activations