© 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. 54297
    Prev
    Next
    INDEX
    Explanations

    radioactive concentrations and exposure

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

    terms related to radiation and radioactive materials, including isotopes, nuclear measurements, and contamination.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    utat
    -0.77
    jei
    -0.76
    motic
    -0.75
    obacter
    -0.74
    初步
    -0.74
    ेंस
    -0.73
    yty
    -0.72
    ğına
    -0.71
    HBox
    -0.71
    词
    -0.71
    POSITIVE LOGITS
     radionuc
    1.01
     összefoglal
    0.88
     radio
    0.83
    Bq
    0.78
    Inhalation
    0.76
     long
    0.75
     радио
    0.74
    Suk
    0.73
    鮑
    0.72
    indari
    0.71
    Activations Density 0.046%

    No Known Activations