© 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. 127961
    Prev
    Next
    INDEX
    Explanations

    to

    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
    arity
    -0.06
     checks
    -0.06
     year
    -0.06
    يرة
    -0.06
     आवर
    -0.06
    ओके
    -0.05
     caching
    -0.05
     Glenn
    -0.05
    itudinal
    -0.05
    Year
    -0.05
    POSITIVE LOGITS
    Após
    0.07
     smoked
    0.07
    なくても
    0.06
     nepot
    0.06
     atrak
    0.06
    🤢
    0.06
     без
    0.06
     kinship
    0.06
     aggress
    0.05
     mirada
    0.05
    Activations Density 0.025%

    No Known Activations