© 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. 42404
    Prev
    Next
    INDEX
    Explanations

    point in time statements

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

    The neuron is responsive to semantically rich content words—key nouns, adjectives, and verbs that carry informational or emphasis weight in the text.

    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
     =
    -1.60
     nhưng
    -1.33
     Two
    -1.30
     ONLY
    -1.29
     abbiano
    -1.24
    ordinator
    -1.23
    μος
    -1.23
    就像是
    -1.22
     undergone
    -1.22
     meist
    -1.22
    POSITIVE LOGITS
     ć
    1.29
     champignons
    1.26
     vandaag
    1.25
     inmiddels
    1.23
     normaal
    1.22
     abus
    1.22
     anex
    1.20
     geschikt
    1.19
     indo
    1.18
     cdr
    1.18
    Activations Density 0.306%

    No Known Activations