© 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. 130470
    Prev
    Next
    INDEX
    Explanations

    This invention, I had, Q:

    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
     enables
    -0.07
     enable
    -0.07
    óf
    -0.07
     ঘুমের
    -0.06
     കര
    -0.06
     һ
    -0.06
     endeavors
    -0.06
    சித்து
    -0.06
    affiliation
    -0.06
     youtube
    -0.06
    POSITIVE LOGITS
     Proceedings
    0.06
    ）（
    0.06
     masculine
    0.06
     sx
    0.06
     denne
    0.06
     ہتھی
    0.06
     რო
    0.05
    믹
    0.05
     typically
    0.05
    md
    0.05
    Activations Density 0.001%

    No Known Activations