© 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. 25070
    Prev
    Next
    INDEX
    Explanations

    years of

    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
     momentary
    -1.38
     ngay
    -1.29
     momentarily
    -1.17
     heut
    -1.09
    talt
    -1.06
    drage
    -1.05
     early
    -1.05
    HomeComponent
    -1.03
    Descrizione
    -1.01
    Zitat
    -1.00
    POSITIVE LOGITS
    ⎝
    1.12
     this
    1.07
    صیل
    1.05
    ⫹
    1.05
     только
    1.05
     adulta
    0.97
     nilai
    0.91
     what
    0.91
    них
    0.90
     intensa
    0.90
    Activations Density 0.107%

    No Known Activations