© 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. 104440
    Prev
    Next
    INDEX
    Explanations

    printed informational material

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

    The neuron activates on words naming printed or supplementary educational/marketing materials (e.g. brochures, booklets, guides, posters, notebooks).

    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
     in
    -1.48
     "
    -1.13
     L
    -1.09
    O
    -1.08
    一言
    -1.08
     #
    -1.05
     
    -1.02
     --
    -1.01
    columbia
    -0.98
     after
    -0.97
    POSITIVE LOGITS
    unesse
    1.27
     pérd
    1.27
     rédig
    1.25
     accompagner
    1.20
     containing
    1.18
     booklet
    1.18
     papiers
    1.16
     estampa
    1.16
    .}(
    1.16
     leaflet
    1.15
    Activations Density 0.057%

    No Known Activations