© 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. 34637
    Prev
    Next
    INDEX
    Explanations

    Runciman, Runje, Rountree, Runcorn

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

    The neuron identifies tokens containing the letter sequence “run,” regardless of case.

    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
     deshalb
    -0.81
     handen
    -0.78
    tori
    -0.77
    kező
    -0.76
    uerdo
    -0.75
    ≠
    -0.74
     beno
    -0.73
    🆁
    -0.73
    kken
    -0.73
     콘
    -0.73
    POSITIVE LOGITS
    женных
    0.80
    Equations
    0.76
    שע
    0.73
    heur
    0.72
     代表
    0.72
    tská
    0.71
     proven
    0.71
    ldots
    0.69
     processed
    0.69
    Equation
    0.68
    Activations Density 0.032%

    No Known Activations