© 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. 116452
    Prev
    Next
    INDEX
    Explanations

    from sources or packages

    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
     những
    -0.06
    వి
    -0.06
     memainkan
    -0.06
    圖像
    -0.06
    =
    -0.06
     emanating
    -0.06
    为
    -0.06
     बिंदुओं
    -0.06
    lerle
    -0.06
     अवेलेबल
    -0.06
    POSITIVE LOGITS
    決定
    0.07
     এন্ড
    0.06
     utas
    0.06
    หนด
    0.06
     대부분
    0.06
     siden
    0.06
     안내
    0.06
    toDate
    0.06
    决定
    0.06
     sofort
    0.06
    Activations Density 0.001%

    No Known Activations