© 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. 128941
    Prev
    Next
    INDEX
    Explanations

    notable things

    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
     некоторые
    -0.07
     사람들이
    -0.07
     برخی
    -0.06
     অপরি
    -0.06
     wäre
    -0.06
    私が
    -0.06
     some
    -0.06
     ряд
    -0.06
     многие
    -0.06
     कुछ
    -0.06
    POSITIVE LOGITS
    atien
    0.07
     інших
    0.06
     keeper
    0.06
    ⱱ
    0.06
    🧍
    0.06
    อื่นๆ
    0.06
     odorless
    0.06
     Otros
    0.06
    Otros
    0.06
     druge
    0.06
    Activations Density 0.011%

    No Known Activations