© 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. 129270
    Prev
    Next
    INDEX
    Explanations

    vacation rentals

    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
     برخی
    -0.09
     bazı
    -0.08
     algunas
    -0.08
     algunos
    -0.08
     birçok
    -0.07
     alguns
    -0.07
     Alguns
    -0.07
     some
    -0.07
     некоторых
    -0.07
     Including
    -0.06
    POSITIVE LOGITS
    Einstein
    0.07
     unbelievably
    0.06
     Eso
    0.06
     astounding
    0.06
     ইত্যাদি
    0.06
     ১৯৯
    0.06
     búsqueda
    0.05
    odings
    0.05
    Devil
    0.05
    Eso
    0.05
    Activations Density 0.003%

    No Known Activations