© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118643
    Prev
    Next
    INDEX
    Explanations

    code keywords get method

    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
    btw
    -0.07
    BTW
    -0.06
     btw
    -0.06
     :}
    -0.06
     aka
    -0.06
     kısm
    -0.06
    also
    -0.06
     kwest
    -0.06
     শুধু
    -0.06
    this
    -0.06
    POSITIVE LOGITS
     облада
    0.06
     что
    0.06
    exper
    0.06
     near
    0.06
     опыт
    0.06
     первая
    0.06
     Antibodies
    0.06
    िक्शन
    0.06
     using
    0.06
     первый
    0.06
    Activations Density 0.001%

    No Known Activations