© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130399
    Prev
    Next
    INDEX
    Explanations

    The neuron highlights semantically rich “content” words (nouns, verbs, adjectives, etc.) and suppresses common function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    late appreciation or recognition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     oaths
    -0.92
    voyez
    -0.91
    新た
    -0.86
    逊
    -0.82
     infallib
    -0.81
     リゾート
    -0.80
     sorento
    -0.78
     Svetlana
    -0.78
    overe
    -0.77
    यार
    -0.77
    POSITIVE LOGITS
     ignored
    1.08
     appreciate
    1.05
    unrecognized
    1.00
     unrecognized
    1.00
     only
    0.96
    理解
    0.91
     appreciated
    0.91
     ignore
    0.90
     undervalued
    0.90
     appreciation
    0.89
    Activations Density 0.052%

    No Known Activations