© 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. 55710
    Prev
    Next
    INDEX
    Explanations

    atomic absorption spectrometry

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

    scientific measurement and analysis techniques, particularly spectroscopy and spectrometry methods.

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

    The neuron strongly activates on mentions of analytical instrumentation methods—especially various forms of absorption spectrometry.

    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
     crítico
    -0.80
     الدر
    -0.73
    ల్ల
    -0.71
    isOk
    -0.71
     sculptural
    -0.71
    ("""
    -0.71
     игро
    -0.70
    deti
    -0.70
    Dimensioni
    -0.69
    य़
    -0.69
    POSITIVE LOGITS
     spectra
    1.40
     flame
    1.39
     absorption
    1.27
     Spectroscopy
    1.23
     spectrum
    1.22
     spectral
    1.22
     spectroscopy
    1.20
    flame
    1.19
     Flame
    1.19
     Spectra
    1.18
    Activations Density 0.029%

    No Known Activations