© 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. 116877
    Prev
    Next
    INDEX
    Explanations

    father john

    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
    不
    -0.06
     pouco
    -0.06
     innych
    -0.06
     despite
    -0.06
    が
    -0.06
     মাদ
    -0.06
    Despite
    -0.06
     שה
    -0.06
     बेशक
    -0.06
     на
    -0.06
    POSITIVE LOGITS
     calculus
    0.07
     essayer
    0.07
     observers
    0.06
     координатами
    0.06
    第三
    0.06
     connected
    0.06
     third
    0.06
     masses
    0.06
     troisième
    0.06
    ಗಳಲ್ಲಿ
    0.06
    Activations Density 0.002%

    No Known Activations