© 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. 1796
    Prev
    Next
    INDEX
    Explanations

    criticism or attack

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

    The neuron fires on phrases indicating that someone or something is being criticized or attacked—especially on the “under fire” construction.

    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
    They
    -1.72
     innumerable
    -1.50
     other
    -1.48
     Some
    -1.45
     still
    -1.45
    lawesi
    -1.43
     ALWAYS
    -1.42
     quickly
    -1.42
     had
    -1.41
     After
    -1.40
    POSITIVE LOGITS
     akumulator
    1.68
    颪
    1.57
     specif
    1.56
     vijf
    1.56
    possibly
    1.55
     ſol
    1.54
     soooo
    1.54
     sooo
    1.53
    specifically
    1.49
     criação
    1.48
    Activations Density 0.054%

    No Known Activations