© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 14968
    Prev
    Next
    INDEX
    Explanations

    spectroscopy and analytical techniques

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

    scientific instrumentation and measurement techniques in research papers.

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

    The neuron strongly activates on mentions of specialized analytical instrumentation (e.g. coupling verbs and equipment names like “coupled,” “FT-IR,” “ATR,” “MALDI-TOF,” “diamond accessory,” etc.), i.e. it’s looking for references to scientific instruments and their configurations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     السياس
    -1.15
    ãe
    -1.14
     parmi
    -1.13
    among
    -1.08
    根据
    -1.05
    :
    -1.02
     decide
    -1.02
    atop
    -1.00
     according
    -0.99
     embarazadas
    -0.99
    POSITIVE LOGITS
     at
    1.30
     sowohl
    1.25
     both
    1.23
    踔
    1.20
     también
    1.14
     både
    1.13
    ópolis
    1.11
     zowel
    1.11
    детский
    1.09
    девушка
    1.09
    Activations Density 0.012%

    No Known Activations