© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130997
    Prev
    Next
    INDEX
    Explanations

    PDF report / article

    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
     ಇದನ್ನು
    -0.06
     মাঝামা
    -0.06
    ərbaycan
    -0.06
     compilation
    -0.06
     forskj
    -0.06
     amalgamation
    -0.06
     generous
    -0.06
     forskellige
    -0.06
    ]]);
    -0.06
     सेवाएं
    -0.06
    POSITIVE LOGITS
    瞥
    0.07
     impeded
    0.06
    畚
    0.06
     JULY
    0.06
     বক্তব্যের
    0.06
     అలా
    0.06
     Prometheus
    0.06
    తులు
    0.06
     July
    0.06
     moeten
    0.06
    Activations Density 0.019%

    No Known Activations