© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 117974
    Prev
    Next
    INDEX
    Explanations

    Q: disclosure

    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
     테스트
    -0.07
     wo
    -0.06
     després
    -0.06
     设计
    -0.06
     شخصیت
    -0.06
     design
    -0.06
     ಶ್ರೀ
    -0.06
    ことができます
    -0.06
     discoveries
    -0.06
     juga
    -0.06
    POSITIVE LOGITS
     blatantly
    0.06
     auparavant
    0.06
     ஒன்றாக
    0.06
     एके
    0.06
    enumerate
    0.06
     undocumented
    0.05
     conjunction
    0.05
     ক্রো
    0.05
    Attrib
    0.05
    袴
    0.05
    Activations Density 0.002%

    No Known Activations