© 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. 10-GEMMASCOPE-RES-131K
    7. 43418
    Prev
    Next
    INDEX
    Explanations

    recognized by

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

    The neuron activates on occurrences of “recognize” (and its morphological variants such as recognize, recognises, recognized, recognition).

    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
     estos
    -1.91
     diesem
    -1.77
     When
    -1.59
    鹛
    -1.59
    ни
    -1.57
     These
    -1.54
     Description
    -1.51
     нее
    -1.50
    形象
    -1.48
    ',
    -1.48
    POSITIVE LOGITS
    although
    1.40
     which
    1.32
     tradução
    1.29
     vermelhas
    1.29
     pájaro
    1.28
    seitigen
    1.27
     that
    1.27
    尔的
    1.24
     famílias
    1.23
    even
    1.22
    Activations Density 0.025%

    No Known Activations