© 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. 63136
    Prev
    Next
    INDEX
    Explanations

    isotopic analysis and dating

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

    scientific text related to geology, isotopes, and analytical chemistry methods.

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

    The neuron strongly activates on technical scientific measurement terms—especially references to isotope‐based dating and analysis methods (e.g. “high‐precision U–Pb geochronology,” stable‐isotope protocols, growth rings, etc.).

    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
    NullCheck
    -0.82
    äter
    -0.80
     PyTuple
    -0.79
    ウザ
    -0.77
     interesa
    -0.75
    ="<
    -0.74
     niños
    -0.74
    anode
    -0.73
    StatusBar
    -0.72
    ्यो
    -0.72
    POSITIVE LOGITS
     isotopic
    0.96
     chemistry
    0.91
    ジュアル
    0.85
     analysis
    0.85
     fauna
    0.84
     petro
    0.84
     dating
    0.82
    竅
    0.82
     Magento
    0.80
     abound
    0.79
    Activations Density 0.017%

    No Known Activations