© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72126
    Prev
    Next
    INDEX
    Explanations

    comparisons of quantity or degree

    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
    Not in Any Lists

    No Comments

    Negative Logits
     it
    -1.48
     this
    -1.26
    ﺀ
    -1.16
    不忘
    -1.08
     würd
    -1.01
    ְל
    -1.00
     lhes
    -0.98
     выбрать
    -0.98
    beyaz
    -0.98
    vestidos
    -0.98
    POSITIVE LOGITS
     more
    1.52
     approximately
    1.48
     much
    1.33
     roughly
    1.21
     nearly
    1.20
     less
    1.18
     significantly
    1.18
     légèrement
    1.17
    approximately
    1.16
     almost
    1.15
    Activations Density 0.041%

    No Known Activations