© 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. 116546
    Prev
    Next
    INDEX
    Explanations

    sure followed by you, that, the

    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
     likely
    -0.07
     možda
    -0.07
    ிருந்தால்
    -0.06
    startsWith
    -0.06
     Mungkin
    -0.06
     Vielleicht
    -0.06
     jeśli
    -0.06
     Likely
    -0.06
     mungkin
    -0.06
     dacă
    -0.06
    POSITIVE LOGITS
     আগামী
    0.07
    যখন
    0.07
     shall
    0.06
    即将
    0.06
     শিগ
    0.06
    主要是
    0.06
     an
    0.06
    ⿻
    0.06
     more
    0.06
     পর্যাপ্ত
    0.06
    Activations Density 0.011%

    No Known Activations