© 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. 10-GEMMASCOPE-RES-131K
    7. 61384
    Prev
    Next
    INDEX
    Explanations

    "all about" followed by a noun

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

    The neuron strongly activates on occurrences of the word “about” (in any case) as used in headings or title‐style phrases.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Ottobre
    -1.52
    Your
    -1.49
    According
    -1.48
     tomat
    -1.46
    according
    -1.45
    corpion
    -1.43
     tailles
    -1.43
     véhicules
    -1.41
     tramonto
    -1.41
     Luglio
    -1.40
    POSITIVE LOGITS
    </strong>
    1.84
     pagrind
    1.76
     relaciona
    1.75
     vivid
    1.54
     pasirink
    1.51
     daugiau
    1.48
    </sup>
    1.44
     entendido
    1.42
     confirmado
    1.41
     aukš
    1.41
    Activations Density 0.115%

    No Known Activations