© 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. 6687
    Prev
    Next
    INDEX
    Explanations

    change or initiation

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

    The neuron is selectively activating on past-tense action verbs (i.e. words ending in “-ed”).

    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
    欧式
    -1.32
    あとは
    -1.26
     großzü
    -1.23
     apostar
    -1.19
    それだけ
    -1.19
    承担
    -1.18
     vroe
    -1.16
    最初から
    -1.15
    颍
    -1.14
    แล้ว
    -1.13
    POSITIVE LOGITS
    "،
    1.52
    BitmapFactory
    1.44
     a
    1.41
     by
    1.40
    4
    1.38
    裢
    1.38
    
    1.38
     „
    1.35
    ár
    1.34
    "*
    1.34
    Activations Density 0.185%

    No Known Activations