© 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. 117369
    Prev
    Next
    INDEX
    Explanations

    build tools (gulp, rake, guard)

    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
     даже
    -0.06
     even
    -0.06
    creet
    -0.06
     பெண்
    -0.06
     angegeben
    -0.05
    Even
    -0.05
    different
    -0.05
     раздра
    -0.05
    골
    -0.05
    igans
    -0.05
    POSITIVE LOGITS
     doorstep
    0.07
    圧力
    0.07
     Northrop
    0.06
     havas
    0.06
     transnational
    0.06
     oferta
    0.06
     فرص
    0.06
    க்கப்பட்டுள்ளது
    0.06
     vstup
    0.06
     entry
    0.06
    Activations Density 0.002%

    No Known Activations