© 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. 129801
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on content-bearing “keywords” (major nouns, verbs, and other informative words) rather than function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    information and interaction

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ğini
    -1.23
    
    -1.22
    isling
    -1.21
     devront
    -1.21
    頃から
    -1.15
    cach
    -1.13
    karna
    -1.11
     xong
    -1.11
    私たち
    -1.09
    alad
    -1.08
    POSITIVE LOGITS
     access
    1.59
     information
    1.56
     your
    1.45
     RECOMEND
    1.33
     important
    1.30
     useful
    1.30
     helpful
    1.25
     status
    1.22
     перец
    1.21
     convenient
    1.20
    Activations Density 0.064%

    No Known Activations