© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22126
    Prev
    Next
    INDEX
    Explanations

    as such,

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

    This neuron detects the discourse marker “As such,” introducing a conclusion or inference.

    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
     disser
    -1.72
    廔
    -1.65
     conversa
    -1.60
    ﺢ
    -1.60
     efic
    -1.59
     by
    -1.58
     preju
    -1.55
    鵟
    -1.54
     From
    -1.52
     Temos
    -1.50
    POSITIVE LOGITS
    \
    1.85
     但是
    1.80
    <strong>
    1.70
    但是
    1.69
    1
    1.66
     avaliação
    1.64
     tropicales
    1.64
     possa
    1.63
     THEIR
    1.63
    ков
    1.61
    Activations Density 0.009%

    No Known Activations