© 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. 119723
    Prev
    Next
    INDEX
    Explanations

    asking questions or seeking answers

    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
     their
    -0.07
    adresse
    -0.06
    addr
    -0.06
    那个
    -0.06
     jejich
    -0.06
     адресу
    -0.06
    udius
    -0.06
    地址
    -0.06
     ihrem
    -0.06
    我又
    -0.05
    POSITIVE LOGITS
     خوان
    0.06
     penting
    0.06
    āya
    0.06
     accumulates
    0.06
     likes
    0.06
     اینجا
    0.06
     enjoyed
    0.06
    }=(\
    0.06
     धूम
    0.06
     accumulating
    0.06
    Activations Density 0.013%

    No Known Activations