© 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. 129495
    Prev
    Next
    INDEX
    Explanations

    urls and domain names

    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
     However
    -0.07
     आदित्य
    -0.06
     aos
    -0.06
    oyama
    -0.06
     முற
    -0.06
    Three
    -0.05
     Val
    -0.05
    आर
    -0.05
    T
    -0.05
    Too
    -0.05
    POSITIVE LOGITS
    就可以了
    0.06
    Causes
    0.06
     honorable
    0.06
     Syri
    0.06
    IMENTAL
    0.06
     peralatan
    0.06
     easily
    0.06
     Honorable
    0.06
     antigua
    0.06
     certamente
    0.06
    Activations Density 0.001%

    No Known Activations