© 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. 117140
    Prev
    Next
    INDEX
    Explanations

    bryony

    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
     cuál
    -0.06
     కీలక
    -0.06
     their
    -0.06
    没有
    -0.06
     no
    -0.06
    ığınız
    -0.06
    卦
    -0.06
     heading
    -0.06
    私も
    -0.06
    着急
    -0.06
    POSITIVE LOGITS
     envers
    0.07
    に対して
    0.07
     utiliser
    0.07
     används
    0.07
    に対する
    0.07
     regarding
    0.06
     dùng
    0.06
     людей
    0.06
    Show
    0.06
     enjoys
    0.06
    Activations Density 0.009%

    No Known Activations