© 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. 110943
    Prev
    Next
    INDEX
    Explanations

    atomic number and nuclear properties

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

    text related to atomic and nuclear physics concepts, particularly focusing on elements, atomic numbers, and scientific measurements.

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

    The neuron primarily detects numerical measurements or quantitative tokens in the 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
    Xiv
    -0.81
    Peru
    -0.75
     coriander
    -0.74
    쁨
    -0.73
     Peru
    -0.72
    ⊄
    -0.71
    blink
    -0.71
    Visitation
    -0.70
     arcilla
    -0.70
    Merkmale
    -0.69
    POSITIVE LOGITS
     Z
    2.13
    Z
    1.93
     atomic
    1.87
    atomic
    1.54
     Atomic
    1.42
    Atomic
    1.42
    getZ
    1.20
     nuclear
    1.18
     z
    1.18
     charge
    1.16
    Activations Density 0.055%

    No Known Activations