© 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. 116538
    Prev
    Next
    INDEX
    Explanations

    Bot Detection, technical docs

    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
     یکی
    -0.06
     కొంత
    -0.06
    bien
    -0.06
     THAN
    -0.06
    一家
    -0.06
     another
    -0.06
     algún
    -0.06
     పంట
    -0.06
     يتم
    -0.06
    바이
    -0.06
    POSITIVE LOGITS
     of
    0.06
     цього
    0.06
     này
    0.06
    のに
    0.06
     or
    0.06
     주고
    0.06
     tuần
    0.06
     this
    0.06
    這個
    0.06
     लाइफ
    0.06
    Activations Density 0.001%

    No Known Activations