© 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. 116436
    Prev
    Next
    INDEX
    Explanations

    Warranty, believes, work, diphenyl

    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
     acknowledges
    -0.07
     reikia
    -0.06
     acknowledging
    -0.06
     corresponds
    -0.06
     stojí
    -0.06
     allows
    -0.05
     হাইক
    -0.05
     nicht
    -0.05
    お知らせ
    -0.05
     কথোপকথ
    -0.05
    POSITIVE LOGITS
    :
    0.06
    🏩
    0.06
    ্লাম
    0.06
     vitesse
    0.06
     rápido
    0.06
    鴳
    0.06
    iawan
    0.06
     profund
    0.06
     quoting
    0.06
     मेरा
    0.06
    Activations Density 0.001%

    No Known Activations