© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128030
    Prev
    Next
    INDEX
    Explanations

    arrest, detention, held, stop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     excl
    -0.07
     маленький
    -0.06
     uzav
    -0.06
     étroite
    -0.06
     inklusive
    -0.06
     bawah
    -0.06
     alienated
    -0.06
     excludes
    -0.05
     risking
    -0.05
    -/
    -0.05
    POSITIVE LOGITS
    说
    0.06
    基于
    0.06
     دلیل
    0.06
    量的
    0.06
     theorist
    0.06
     방식
    0.06
    合物
    0.06
    หลัก
    0.06
    这本书
    0.06
    elson
    0.06
    Activations Density 0.001%

    No Known Activations