© 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. 120788
    Prev
    Next
    INDEX
    Explanations

    Sailors

    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
    Not in Any Lists

    No Comments

    Negative Logits
     existing
    -0.06
    三十
    -0.06
     vorhand
    -0.06
    な
    -0.05
     cient
    -0.05
    existing
    -0.05
     recue
    -0.05
    嚕
    -0.05
    传
    -0.05
     சொல்ல
    -0.05
    POSITIVE LOGITS
    indows
    0.07
     attempting
    0.06
     चाहती
    0.06
     دارد
    0.06
     می‌تواند
    0.06
    などに
    0.06
     ಮತ್ತೆ
    0.06
     дизайн
    0.06
    érus
    0.06
    appears
    0.06
    Activations Density 0.001%

    No Known Activations