© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 114174
    Prev
    Next
    INDEX
    Explanations

    corresponds to

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

    The neuron is primarily triggered by descriptive modifier forms—especially words ending in “-ing” (gerunds/participles) or “-ly” (adverbs).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    んでいた
    -1.16
    全体
    -1.06
     quando
    -1.05
    bsen
    -1.04
    まりました
    -1.03
    onBlur
    -1.03
     rám
    -1.03
    jiny
    -1.02
     Vikipedi
    -0.99
    жидан
    -0.97
    POSITIVE LOGITS
     at
    1.25
     filma
    1.19
     bota
    1.19
     saveiro
    1.18
     cuma
    1.16
     sogar
    1.16
    鹀
    1.16
     parola
    1.15
     Ağ
    1.13
     bombas
    1.13
    Activations Density 0.330%

    No Known Activations