© 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. 128759
    Prev
    Next
    INDEX
    Explanations

    housing and facilities

    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
     başta
    -0.07
     studenti
    -0.06
     ஏ
    -0.06
           
    -0.06
                       
    -0.06
                   
    -0.06
    ビジネス
    -0.06
     drei
    -0.06
                              
    -0.06
    ３
    -0.06
    POSITIVE LOGITS
     those
    0.06
     deficiency
    0.06
    нига
    0.06
     implementar
    0.06
     encouraging
    0.06
     हल
    0.06
     Females
    0.06
     Residential
    0.06
     positives
    0.06
     Sản
    0.06
    Activations Density 0.002%

    No Known Activations