© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25596
    Prev
    Next
    INDEX
    Explanations

    revisiting and re-examining

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

    The neuron strongly activates on instances of the prefix “re-” (e.g. revis-, re-, reexam-, revisited) indicating it is looking for words that start with “re” (the “again”/repetition prefix).

    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
    heimer
    -0.77
    baugh
    -0.75
    ceus
    -0.74
     tengah
    -0.73
    🅻
    -0.72
    ión
    -0.72
    ioctl
    -0.72
    接下来的
    -0.72
    sumowanie
    -0.72
    SCOTT
    -0.71
    POSITIVE LOGITS
     revisit
    5.41
     revisited
    5.03
     revis
    4.34
     Revisited
    4.03
     Revis
    2.86
    Revis
    2.81
     reconsider
    2.19
     reconsideration
    1.88
    visited
    1.84
     visited
    1.70
    Activations Density 0.098%

    No Known Activations