© 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. 10-GEMMASCOPE-RES-131K
    7. 10036
    Prev
    Next
    INDEX
    Explanations

    spectroscopy

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

    The neuron identifies the word "spectroscopy" and related scientific measurement techniques.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    这事
    -2.67
     was
    -2.50
     -
    -2.34
     it
    -2.30
     Immobilien
    -2.28
    筇
    -2.25
    -2.16
    licante
    -2.14
    麈
    -2.13
     they
    -2.11
    POSITIVE LOGITS
     ständig
    2.50
    OUTUBE
    2.41
    In
    2.34
    𐄁
    2.34
    牁
    2.27
     أمس
    2.23
    する
    2.20
     ausschließlich
    2.14
    姈
    2.11
     äußerst
    2.09
    Activations Density 0.005%

    No Known Activations