© 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. 130119
    Prev
    Next
    INDEX
    Explanations

    codes, languages, and specific identifiers

    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
     an
    -0.07
    ↵↵↵
    -0.06
     a
    -0.06
    ↵
    -0.06
     
    -0.06
    юро
    -0.05
    ↵↵
    -0.05
     ভাত
    -0.05
     nascent
    -0.05
     dispatch
    -0.05
    POSITIVE LOGITS
    谁
    0.07
     erneut
    0.07
     determines
    0.07
    誰
    0.07
    संर
    0.06
     Convolution
    0.06
    ECTION
    0.06
     көзге
    0.06
     الذين
    0.06
     که
    0.06
    Activations Density 0.005%

    No Known Activations