© 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. 6727
    Prev
    Next
    INDEX
    Explanations

    commenting on things

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ípio
    -2.06
     nella
    -2.05
     они
    -2.02
     носить
    -1.89
     menentukan
    -1.86
    NÍ
    -1.82
    waite
    -1.79
     Things
    -1.79
     необходимо
    -1.75
     étab
    -1.74
    POSITIVE LOGITS
    鹮
    3.03
    苼
    2.50
    ですので
    2.41
     zorgt
    2.20
    .
    2.17
     Houſe
    2.16
    ܃
    2.16
    Пусть
    2.13
     parachoque
    2.11
     mauva
    2.08
    Activations Density 0.004%

    No Known Activations