© 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. 115776
    Prev
    Next
    INDEX
    Explanations

    words after `@` or `from`

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

    The neuron is detecting Java code identifiers, especially dotted package/import names.

    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
     ct
    -0.75
     bogus
    -0.73
    不必
    -0.70
     AND
    -0.68
    xty
    -0.68
     القدم
    -0.67
    لاً
    -0.67
    并非
    -0.67
     mostly
    -0.66
     premise
    -0.66
    POSITIVE LOGITS
     defies
    0.91
     sorts
    0.87
     contention
    0.84
     電気
    0.82
    豺
    0.81
    𝑬
    0.81
    ulados
    0.79
     defy
    0.79
    看了
    0.77
     emocion
    0.76
    Activations Density 0.922%

    No Known Activations