© 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. 116548
    Prev
    Next
    INDEX
    Explanations

    education and professional services

    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
     continued
    -0.08
     continuously
    -0.07
     llegada
    -0.06
     करती
    -0.06
     आयी
    -0.06
     उठता
    -0.06
     đối
    -0.06
    ってくる
    -0.06
    Continued
    -0.06
    ẩu
    -0.06
    POSITIVE LOGITS
     statements
    0.06
     చక్కెర
    0.06
     ios
    0.06
     statement
    0.06
     sugg
    0.06
     ৫
    0.06
     সাত
    0.06
             
    0.06
     Ще
    0.05
     половине
    0.05
    Activations Density 0.002%

    No Known Activations