© 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. 65697
    Prev
    Next
    INDEX
    Explanations

    Reuters mentions or financial data

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

    The neuron detects newswire dateline markers (e.g. the all‐caps location, the “(Reuters)” source tag, and the following dash).

    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
     Tej
    -0.81
    Patience
    -0.78
     Teal
    -0.72
     awalnya
    -0.72
    طفال
    -0.71
     pagină
    -0.71
    éfono
    -0.70
    gamot
    -0.69
    titem
    -0.68
     אר
    -0.68
    POSITIVE LOGITS
     CPUs
    0.94
     ASME
    0.91
     ASEAN
    0.84
    ⎝
    0.81
    ometry
    0.81
     devoured
    0.81
     Trotz
    0.80
     Thumb
    0.80
    owaniu
    0.80
    crombie
    0.79
    Activations Density 0.016%

    No Known Activations