© 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. 25048
    Prev
    Next
    INDEX
    Explanations

    linebackers

    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
     its
    -1.21
     to
    -1.16
    −
    -1.16
     equipment
    -1.16
     system
    -1.12
    media
    -1.12
     instala
    -1.11
    start
    -1.11
     ValueError
    -1.11
    format
    -1.10
    POSITIVE LOGITS
    Execu
    1.41
    sugges
    1.38
    渐变
    1.33
    embra
    1.32
     profondeur
    1.28
     nukes
    1.24
    ování
    1.23
    满是
    1.21
    左边
    1.20
    stolen
    1.20
    Activations Density 0.000%

    No Known Activations