© 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. 119713
    Prev
    Next
    INDEX
    Explanations

    data reduction proxy

    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
     등의
    -0.07
     เพื่อ
    -0.06
     EDTA
    -0.06
    德
    -0.06
     등을
    -0.06
    などの
    -0.06
     beispielsweise
    -0.05
    ielder
    -0.05
     bijvoorbeeld
    -0.05
     například
    -0.05
    POSITIVE LOGITS
     pelo
    0.07
     pelas
    0.07
     pela
    0.07
     नॉर्म
    0.06
     النظام
    0.06
     المقام
    0.06
     அழகான
    0.06
    गड
    0.06
    elif
    0.06
    
    0.05
    Activations Density 0.015%

    No Known Activations