© 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. 22-GEMMASCOPE-RES-131K
    7. 79600
    Prev
    Next
    INDEX
    Explanations

    visual sense, offering, competing

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

    The neuron flags semantically rich content words (key nouns, verbs, adjectives) while ignoring common function words.

    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
     {$\
    -1.22
    atized
    -1.20
    …»
    -1.19
     cojín
    -1.18
    (%)
    -1.17
     ;
    -1.17
     différentes
    -1.16
    本身
    -1.15
     ()
    -1.13
     tinto
    -1.12
    POSITIVE LOGITS
     of
    1.20
     EconPapers
    1.08
    jualan
    1.03
     столо
    1.03
    的气息
    1.02
     Absch
    1.01
    google
    1.01
    re
    1.00
    ötä
    1.00
     next
    0.99
    Activations Density 0.042%

    No Known Activations