© 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. 117327
    Prev
    Next
    INDEX
    Explanations

    progressive chronic

    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
    倌
    -0.06
    भगवान
    -0.06
     হস্তক্ষেপ
    -0.06
     பகு
    -0.06
     samtidig
    -0.06
     simultaneous
    -0.06
     noen
    -0.06
     kombin
    -0.06
     frogs
    -0.06
    合併
    -0.06
    POSITIVE LOGITS
     continually
    0.06
     Islam
    0.06
     gloves
    0.06
     thereafter
    0.06
    Video
    0.06
     т
    0.06
    oper
    0.06
    每日
    0.06
     rapidly
    0.06
    க்குப்
    0.06
    Activations Density 0.007%

    No Known Activations