© 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. 32613
    Prev
    Next
    INDEX
    Explanations

    pages and possessives

    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
     at
    -1.04
     with
    -1.02
     has
    -1.00
     already
    -0.90
     as
    -0.88
     Sorte
    -0.86
     or
    -0.85
     уже
    -0.84
     there
    -0.81
     elég
    -0.81
    POSITIVE LOGITS
    페이지
    1.13
    &=&\
    0.98
    ونم
    0.97
    줬
    0.97
    WriteByte
    0.93
    categorized
    0.93
    ACIAS
    0.90
    twelve
    0.90
     beſt
    0.89
     ferramentas
    0.87
    Activations Density 0.006%

    No Known Activations