© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119727
    Prev
    Next
    INDEX
    Explanations

    Is factor of

    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
     successively
    -0.06
    felt
    -0.06
    㧿
    -0.06
    コンテンツ
    -0.06
     made
    -0.06
     related
    -0.06
     различных
    -0.06
    㮔
    -0.06
    iderm
    -0.06
     thereafter
    -0.06
    POSITIVE LOGITS
     These
    0.07
    These
    0.07
     these
    0.07
    ↵
    0.07
    ските
    0.06
     başarılı
    0.06
     علاقوں
    0.06
     usare
    0.06
     những
    0.06
     what
    0.06
    Activations Density 0.003%

    No Known Activations