© 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. 76195
    Prev
    Next
    INDEX
    Explanations

    RDD, Spark, Scala

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

    The neuron fires on programming‐code tokens—especially numeric literals, punctuation, and identifier fragments typical of code snippets.

    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
    InjectMocks
    -0.81
    iden
    -0.78
    Rio
    -0.65
     villagers
    -0.65
    یب
    -0.65
     Cin
    -0.65
    getSelection
    -0.65
     europ
    -0.64
     classy
    -0.63
     ох
    -0.63
    POSITIVE LOGITS
    RDD
    1.45
     spark
    1.36
     SPARK
    1.34
     Spark
    1.30
    rdd
    1.23
    Spark
    1.20
    spark
    1.12
     scala
    1.00
     Scala
    0.99
    广播
    0.90
    Activations Density 0.047%

    No Known Activations