© 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. 118688
    Prev
    Next
    INDEX
    Explanations

    Court cases and locations

    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
     này
    -0.07
     deze
    -0.06
     कई
    -0.06
     hazırlan
    -0.06
    多く
    -0.06
     این
    -0.06
     According
    -0.06
     đọc
    -0.06
    attenzione
    -0.06
     These
    -0.06
    POSITIVE LOGITS
    .
    0.08
    rent
    0.06
    פשר
    0.06
     где
    0.06
     আপাতত
    0.06
     where
    0.06
     จึง
    0.06
    ཥ
    0.06
    ga
    0.06
    🍰
    0.06
    Activations Density 0.002%

    No Known Activations