© 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. 116663
    Prev
    Next
    INDEX
    Explanations

    SQL INSERT statements

    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
     karena
    -0.07
     bizim
    -0.07
     beinhaltet
    -0.07
    🎆
    -0.07
     eftersom
    -0.07
    😫
    -0.07
    细腻
    -0.07
    沙漠
    -0.06
     Также
    -0.06
     ditambah
    -0.06
    POSITIVE LOGITS
    この
    0.07
     この
    0.06
     可以
    0.06
    ΜΑ
    0.06
     今
    0.06
     お
    0.06
     ঘোষনা
    0.05
    今天
    0.05
     有
    0.05
     ......
    0.05
    Activations Density 0.002%

    No Known Activations