© 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. 22-GEMMASCOPE-RES-131K
    7. 33764
    Prev
    Next
    INDEX
    Explanations

    characterization of scientific processes

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

    scientific terms related to characterization and analysis in research papers.

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

    The neuron fires on instances of the technical term “characterization” (and its morphological variants like “characterize”).

    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
     to
    -1.51
    很赞
    -1.24
     zostanie
    -1.23
     hábiles
    -1.23
     wydaje
    -1.19
    erialization
    -1.16
     邊
    -1.15
    大約
    -1.15
     pertenecen
    -1.14
     ältere
    -1.13
    POSITIVE LOGITS
     of
    2.45
    cestors
    1.32
     помощью
    1.30
    вока
    1.28
     through
    1.28
     avocat
    1.27
     brune
    1.27
     ananas
    1.23
     panik
    1.23
    ”，
    1.22
    Activations Density 0.123%

    No Known Activations