© 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. 60662
    Prev
    Next
    INDEX
    Explanations

    predictions and forecasts

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

    The neuron fires on section or article titles (headings) in sports‐related text.

    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
    📣
    -1.01
    Toluene
    -0.90
     jenis
    -0.84
    ตัวเอง
    -0.84
    стоин
    -0.83
    😐
    -0.82
     Nauka
    -0.81
    😮
    -0.81
    🤨
    -0.80
    šča
    -0.78
    POSITIVE LOGITS
     predictions
    1.74
     prediction
    1.48
     predicted
    1.37
     analysis
    1.23
     rankings
    1.16
    predictions
    1.16
    预测
    1.15
     predicting
    1.14
     who
    1.09
     updated
    1.06
    Activations Density 0.072%

    No Known Activations