© 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. 22-GEMMASCOPE-RES-131K
    7. 64378
    Prev
    Next
    INDEX
    Explanations

    stages and sequences

    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
    Negative Logits
     envoyer
    -1.04
     préparer
    -1.02
     emplois
    -0.96
    ismatic
    -0.94
     papiers
    -0.93
    OTER
    -0.92
    脑袋
    -0.90
    created
    -0.90
     предотвра
    -0.89
     actualité
    -0.89
    POSITIVE LOGITS
     eventually
    1.67
    เริ่ม
    1.66
     first
    1.59
     Initially
    1.58
     phase
    1.54
     gradually
    1.52
     Eventually
    1.52
     stages
    1.46
     initially
    1.46
     Typically
    1.41
    Activations Density 0.058%

    No Known Activations