© 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. 130605
    Prev
    Next
    INDEX
    Explanations

    parentheses and variables like `i`

    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
     if
    -0.08
     Един
    -0.07
     też
    -0.07
    뀨
    -0.07
     единственный
    -0.07
    Э
    -0.07
     Když
    -0.06
     when
    -0.06
    와
    -0.06
     této
    -0.06
    POSITIVE LOGITS
     still
    0.06
    increases
    0.06
     allowed
    0.05
     simple
    0.05
     ["
    0.05
    不超过
    0.05
    ...).
    0.05
     خلال
    0.05
     było
    0.05
    ?).
    0.05
    Activations Density 0.008%

    No Known Activations