© 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. 120890
    Prev
    Next
    INDEX
    Explanations

    page up/down

    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
    啟用
    -0.07
    电话
    -0.07
    簡易
    -0.06
    审批
    -0.06
     客
    -0.06
    启用
    -0.06
     শতকরা
    -0.06
     customizable
    -0.06
     simplistic
    -0.06
     雨
    -0.06
    POSITIVE LOGITS
     should
    0.07
     persists
    0.06
     appears
    0.06
     неодно
    0.06
    垠
    0.06
     does
    0.05
     শরণার্থীদের
    0.05
    pt
    0.05
     intentar
    0.05
     работода
    0.05
    Activations Density 0.002%

    No Known Activations