© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2620
    Prev
    Next
    INDEX
    Explanations

    records and tracking

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

    The neuron specializes in picking out quantitative and record-related data—especially years, numbers, and statistics indicating “on record,” “since,” counts, and similar numeric benchmarks.

    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
    章节错误
    -0.85
    ladı
    -0.81
     haircuts
    -0.79
    €
    -0.78
    見えて
    -0.75
    ramen
    -0.75
    cnico
    -0.75
     oligonucleotide
    -0.74
    ᵘ
    -0.73
    Tours
    -0.73
    POSITIVE LOGITS
     records
    6.47
    records
    5.19
    Records
    4.69
     Records
    4.56
     record
    4.34
     RECORDS
    4.03
    record
    3.89
    记录
    3.44
    Record
    3.33
    記録
    3.19
    Activations Density 0.097%

    No Known Activations