© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 23869
    Prev
    Next
    INDEX
    Explanations

    expresses possibility or certainty

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

    The neuron specializes in picking out the main clause predicate—especially copulas (“is,” “are,” “there is/are”) and other primary verbs or auxiliaries that introduce a statement or judgment.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     such
    -1.63
     are
    -1.34
     since
    -1.18
    getResultList
    -1.16
     ранее
    -1.16
     Depuis
    -1.15
    ﺯ
    -1.13
     SUCH
    -1.12
     innova
    -1.10
     réglementation
    -1.10
    POSITIVE LOGITS
     you
    1.39
     be
    1.39
     fisuras
    1.27
    всегда
    1.26
     maravillas
    1.23
     joyas
    1.23
     heureuse
    1.21
     atractiva
    1.20
     destinées
    1.20
     />';
    1.16
    Activations Density 0.128%

    No Known Activations