© 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. 11987
    Prev
    Next
    INDEX
    Explanations

    spectroscopic techniques by

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

    scientific research techniques and methodology, particularly experimental measurements and analysis methods.

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

    The neuron fires on mentions of detailed experimental characterization methods (e.g. spectroscopy or interface‐probing techniques).

    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
     steuer
    -0.81
     discretization
    -0.79
    ÂN
    -0.77
    ᠌
    -0.77
     chiến
    -0.75
     الوضع
    -0.75
    reli
    -0.74
    ⠣
    -0.74
     dėl
    -0.74
     الطبي
    -0.74
    POSITIVE LOGITS
     Raman
    1.45
     NMR
    1.14
     UV
    1.10
    Raman
    1.10
     spectroscopy
    1.09
     neutron
    1.05
    UV
    1.03
     fluorescence
    0.98
    NMR
    0.97
     Laser
    0.96
    Activations Density 0.250%

    No Known Activations