© 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. 128855
    Prev
    Next
    INDEX
    Explanations

    parametric, dependent, specific

    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
     Kosten
    -0.06
    路径
    -0.06
     coûts
    -0.06
     경로
    -0.06
     iniziamo
    -0.06
    瘀
    -0.06
     चाइल्ड
    -0.06
    大小
    -0.06
     kształ
    -0.06
     leisurely
    -0.06
    POSITIVE LOGITS
     specific
    0.06
     அனுமதிக்க
    0.06
     একত্রিত
    0.06
    specific
    0.06
    apar
    0.06
     अतिक्रमण
    0.06
    י
    0.05
     جائز
    0.05
     subcontinent
    0.05
    gram
    0.05
    Activations Density 0.002%

    No Known Activations