© 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. 19023
    Prev
    Next
    INDEX
    Explanations

    specific instances after "such"

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

    This neuron detects occurrences of the word “such” (typically as an intensifier before a noun or adjective).

    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
    ﹍﹍
    -1.94
     unbelievably
    -1.92
    ཿ
    -1.84
     soooo
    -1.83
     sooo
    -1.79
     exceptionally
    -1.77
    その他の
    -1.73
     insanely
    -1.73
    every
    -1.68
     deliciously
    -1.66
    POSITIVE LOGITS
     what
    2.00
     one
    1.82
     provide
    1.78
     epitom
    1.75
     create
    1.67
     having
    1.62
     give
    1.61
     longstanding
    1.59
     two
    1.59
     arguably
    1.59
    Activations Density 0.032%

    No Known Activations