© 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. 70440
    Prev
    Next
    INDEX
    Explanations

    introductory clarifications

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

    The neuron spotlights document-structuring or discourse marker tokens—words that introduce new sections or notes (e.g. “Note,” “Examples,” “Sensor Data,” “This,” “The,” etc.).

    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
     begin
    -1.26
     tells
    -1.13
     begins
    -1.13
     vervolgens
    -1.09
     explains
    -1.07
     began
    -1.07
     daarom
    -1.07
     Instead
    -1.06
     give
    -1.05
     them
    -1.04
    POSITIVE LOGITS
    despite
    1.36
     not
    1.34
     optik
    1.32
     suicidio
    1.25
     bukanlah
    1.23
     stadion
    1.20
     Congresso
    1.18
     romantis
    1.16
     Remarque
    1.16
     không
    1.15
    Activations Density 0.031%

    No Known Activations