© 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. 128202
    Prev
    Next
    INDEX
    Explanations

    common library project

    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
    Canonical
    -0.06
     Versions
    -0.06
    chte
    -0.06
    ገኛ
    -0.06
     вероятность
    -0.06
     Vener
    -0.06
     dealings
    -0.06
     آدمی
    -0.06
    を追加
    -0.05
     labai
    -0.05
    POSITIVE LOGITS
    始めた
    0.07
     alone
    0.07
     partenza
    0.06
     themselves
    0.06
     ತಮ್ಮ
    0.06
     memulai
    0.06
     البدايه
    0.06
     iniciando
    0.06
     their
    0.06
    erer
    0.06
    Activations Density 0.005%

    No Known Activations