© 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. 81213
    Prev
    Next
    INDEX
    Explanations

    leader tenure

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

    The neuron is detecting spans that convey numeric information—counts, measurements, dates, percentages, and other statistical figures.

    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
     terdekat
    -0.85
     traccia
    -0.79
     prieten
    -0.78
    itsub
    -0.77
     резер
    -0.75
     betrieb
    -0.74
     膠
    -0.74
    委員
    -0.73
     pendukung
    -0.73
     Support
    -0.73
    POSITIVE LOGITS
     helm
    3.61
     hel
    2.78
     steering
    2.19
    helm
    2.06
     Helm
    1.98
     leadership
    1.89
     leader
    1.87
    Helm
    1.78
    steering
    1.68
    leader
    1.61
    Activations Density 0.054%

    No Known Activations