© 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. 120202
    Prev
    Next
    INDEX
    Explanations

    basal

    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
    另一个
    -0.06
     умира
    -0.06
    에서
    -0.06
     accur
    -0.06
    一个是
    -0.06
     appartenant
    -0.06
    lovely
    -0.06
     விரை
    -0.06
     более
    -0.06
    不像
    -0.06
    POSITIVE LOGITS
     धमाल
    0.06
     ständig
    0.06
     بالفعل
    0.06
     pamoja
    0.06
    DEFAULT
    0.06
     Controversy
    0.06
    或许
    0.06
    কাব
    0.06
     poderá
    0.06
    デフォルト
    0.06
    Activations Density 0.057%

    No Known Activations