© 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. 66261
    Prev
    Next
    INDEX
    Explanations

    radiation and radiolysis

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

    terms related to radiation, including "irradiation", "gamma rays", and "radiolysis" in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron primarily fires on numeric or alphanumeric tokens—years, doses, counts, and other measurement-style numbers.

    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
     Ofen
    -0.75
    tego
    -0.74
     Albin
    -0.73
     sakit
    -0.69
     rodin
    -0.68
     Popcorn
    -0.68
    Porta
    -0.67
     devido
    -0.67
    鍛
    -0.66
     נח
    -0.66
    POSITIVE LOGITS
     irradiation
    1.49
     irradiated
    1.19
    Radiation
    1.10
     радиа
    1.09
     radiation
    1.07
     radiotherapy
    1.06
     Gamma
    1.04
    辐
    1.04
     irradi
    1.04
     dosi
    1.03
    Activations Density 0.042%

    No Known Activations