© 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. 9336
    Prev
    Next
    INDEX
    Explanations

    lists of information

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

    This neuron fires on the word “of” when it appears in document or section headings (e.g. “Summary of…,” “Overview of…,” “List of…,” 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
     trajets
    -1.55
     akrab
    -1.52
     œufs
    -1.52
     carottes
    -1.52
    ølge
    -1.51
    itizing
    -1.43
     helicóptero
    -1.39
    köp
    -1.38
    förm
    -1.36
     diinginkan
    -1.36
    POSITIVE LOGITS
     to
    1.90
     not
    1.73
    L
    1.45
    M
    1.44
    P
    1.41
    S
    1.40
    T
    1.40
     long
    1.40
     Many
    1.38
     Sometimes
    1.37
    Activations Density 0.234%

    No Known Activations