© 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. 118273
    Prev
    Next
    INDEX
    Explanations

    code keywords like include, import, use

    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
    ?
    -0.06
    なの
    -0.06
     moiety
    -0.06
     dejo
    -0.05
     ALSO
    -0.05
    шений
    -0.05
    cev
    -0.05
    も
    -0.05
     anions
    -0.05
     সজ্জিত
    -0.05
    POSITIVE LOGITS
     ketika
    0.07
     рассказыва
    0.07
     when
    0.06
     jusqu
    0.06
     wanneer
    0.06
     until
    0.06
     त्याच्या
    0.06
     calculate
    0.06
     wraz
    0.06
     it
    0.06
    Activations Density 0.001%

    No Known Activations