© 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. 73363
    Prev
    Next
    INDEX
    Explanations

    such [noun]

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

    The neuron specifically detects the word “such.”

    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
     entram
    -1.81
    嵛
    -1.79
    君は
    -1.70
    猡
    -1.69
     valo
    -1.68
     apesar
    -1.62
    荜
    -1.58
     cef
    -1.56
     todav
    -1.55
     eviden
    -1.55
    POSITIVE LOGITS
     a
    1.71
     olisi
    1.66
    ,“
    1.59
    :“
    1.52
    ส์
    1.51
    latter
    1.48
     valmis
    1.47
     ‘
    1.45
     właśnie
    1.45
     provincias
    1.44
    Activations Density 0.055%

    No Known Activations