© 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. 120355
    Prev
    Next
    INDEX
    Explanations

    newspaper names and days

    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
     old
    -0.07
    broadcast
    -0.06
    journalist
    -0.06
    old
    -0.06
     Journalist
    -0.06
     periodistas
    -0.06
     broadcast
    -0.06
     solche
    -0.06
     লাগছে
    -0.06
    ząc
    -0.06
    POSITIVE LOGITS
    xcodeproj
    0.07
     নিয়ে
    0.06
     tilby
    0.06
     ئێ
    0.06
    <0xC2>
    0.06
    স্বপ্ন
    0.06
     mystery
    0.06
    天天
    0.06
     يوم
    0.06
     euch
    0.06
    Activations Density 0.014%

    No Known Activations