© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130455
    Prev
    Next
    INDEX
    Explanations

    css links and imports

    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
     했
    -0.06
     полноцен
    -0.06
     ¿?
    -0.06
     रीजनिंग
    -0.06
    usually
    -0.06
    Normally
    -0.06
     राय
    -0.06
     সমঝো
    -0.06
    Balanced
    -0.06
     normalmente
    -0.06
    POSITIVE LOGITS
     those
    0.08
     our
    0.08
     naszych
    0.07
    those
    0.06
     nuestros
    0.06
     magnitude
    0.06
     những
    0.06
     various
    0.06
    我们将
    0.06
    ಕ್ಕೂ
    0.06
    Activations Density 0.004%

    No Known Activations