© 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. 129800
    Prev
    Next
    INDEX
    Explanations

    medical or technical terms followed by numbers in parentheses

    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
     主
    -0.07
     Different
    -0.07
    改正
    -0.07
     Another
    -0.07
    日前
    -0.06
     Even
    -0.06
    谷歌
    -0.06
     ANOTHER
    -0.06
     with
    -0.06
    Another
    -0.06
    POSITIVE LOGITS
    вшихся
    0.06
    generally
    0.06
     
    0.06
     два
    0.06
     ≤
    0.06
     generally
    0.05
    (?
    0.05
    は
    0.05
     няма
    0.05
    relatively
    0.05
    Activations Density 0.006%

    No Known Activations