© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 229558
    Prev
    Next
    INDEX
    Explanations

    privilege to work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     käytt
    0.44
    ù
    0.44
    ometimes
    0.42
     fö
    0.42
     Re
    0.41
     印
    0.41
    ">
    0.41
     죄
    0.40
     mercury
    0.40
     மாய
    0.40
    POSITIVE LOGITS
    ант
    0.50
    Businesses
    0.49
    𝒚
    0.49
    леду
    0.46
    Edu
    0.46
     बॉल
    0.46
    ंस
    0.46
    Pedidos
    0.46
    もり
    0.46
    кал
    0.46
    Activations Density 0.001%

    No Known Activations