© 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. 116956
    Prev
    Next
    INDEX
    Explanations

    new folder or file

    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
     সমস্ত
    -0.06
    一共
    -0.06
     생각
    -0.06
    ിലുള്ള
    -0.06
    margin
    -0.06
     mk
    -0.05
    ്‍
    -0.05
    primer
    -0.05
    સ્તુ
    -0.05
     ആവശ്യ
    -0.05
    POSITIVE LOGITS
    口气
    0.06
     Moż
    0.06
     FULL
    0.06
    िएट
    0.06
     DATA
    0.06
     श्रमिक
    0.06
     सलाहकार
    0.06
    uring
    0.05
     Woolf
    0.05
     hout
    0.05
    Activations Density 0.104%

    No Known Activations