© 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. 32334
    Prev
    Next
    INDEX
    Explanations

    iteration and collections

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

    This neuron strongly activates on Java code tokens (keywords, method calls, punctuation, and other syntax elements in 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
     persuaded
    -1.06
     arrays
    -0.82
     gerais
    -0.82
     regulador
    -0.77
    fgets
    -0.77
    だよ
    -0.74
     persuasive
    -0.74
    umbu
    -0.74
     persuading
    -0.74
     mapping
    -0.73
    POSITIVE LOGITS
    Iterator
    2.52
     Iterator
    2.17
     iterator
    1.43
    Set
    1.17
    IEnumerator
    1.05
    迭代
    1.05
     Set
    1.04
     for
    1.01
     IEnumerator
    1.01
     Enumeration
    0.96
    Activations Density 0.005%

    No Known Activations