© 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. 22-GEMMASCOPE-RES-131K
    4. 357
    Prev
    Next
    INDEX
    Explanations

    company, studio, label, operator, partner, by, of

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

    The neuron fires on attribution phrases (“provided by,” “from,” “operator,” etc.) that credit or identify organizations or other entities responsible for something.

    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
     vijf
    -1.45
     tromper
    -1.43
     étages
    -1.39
     gedachten
    -1.35
     fameux
    -1.34
     mediocre
    -1.34
     boîtes
    -1.34
     véritables
    -1.34
     dizaines
    -1.34
     occuper
    -1.33
    POSITIVE LOGITS
     our
    1.82
     in
    1.82
     with
    1.75
     one
    1.70
     this
    1.66
     There
    1.66
     at
    1.61
     Two
    1.58
     aptly
    1.57
     oddly
    1.48
    Activations Density 0.103%

    No Known Activations