© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38878
    Prev
    Next
    INDEX
    Explanations

    defining terminology and meanings

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

    The neuron activates on passages that are explicitly defining or clarifying terminology—that is, when the text discusses precise meanings or semantics of terms.

    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
     andato
    -1.03
    طراحی
    -0.98
    ător
    -0.94
    XmlIgnore
    -0.94
    مشخصات
    -0.92
     ダンス
    -0.91
     Nacionales
    -0.91
    ích
    -0.91
     BIBLIOGRAPHY
    -0.90
    onents
    -0.90
    POSITIVE LOGITS
     definition
    1.39
     defining
    1.30
     definitions
    1.29
     confusion
    1.27
    定義
    1.24
     terminology
    1.22
     nomenclature
    1.20
     define
    1.16
     confusing
    1.16
     classification
    1.12
    Activations Density 0.193%

    No Known Activations