© 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. 128961
    Prev
    Next
    INDEX
    Explanations

    legal appeals

    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
    more
    -0.07
    には
    -0.06
     under
    -0.06
     loro
    -0.06
    〇
    -0.05
     ды
    -0.05
    MORE
    -0.05
     mysqli
    -0.05
    remember
    -0.05
     узна
    -0.05
    POSITIVE LOGITS
     Rapid
    0.07
    Rapid
    0.07
     rapidly
    0.07
    rapid
    0.07
     rapid
    0.06
     zatím
    0.06
     stockage
    0.06
     প্রত্যাবর্তন
    0.06
     থাকবে
    0.06
     নির্ধারণ
    0.06
    Activations Density 0.003%

    No Known Activations