© 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. 119500
    Prev
    Next
    INDEX
    Explanations

    individually and

    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
    atche
    -0.06
    还需要
    -0.06
     Default
    -0.06
     acto
    -0.06
    வாய
    -0.06
     театра
    -0.06
    тво
    -0.06
     जेटली
    -0.05
     performing
    -0.05
    ↵↵
    -0.05
    POSITIVE LOGITS
    Millions
    0.06
    यान
    0.06
     อุ
    0.06
     latest
    0.06
     this
    0.06
     während
    0.06
     when
    0.06
     kids
    0.06
     millions
    0.06
     znak
    0.06
    Activations Density 0.001%

    No Known Activations