© 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. 116682
    Prev
    Next
    INDEX
    Explanations

    instructions provided

    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
     जोड़ने
    -0.06
    釦
    -0.06
     לד
    -0.06
    添加
    -0.06
     addition
    -0.06
    就可以
    -0.06
     എന്ന
    -0.06
     aggi
    -0.06
     その
    -0.06
     их
    -0.06
    POSITIVE LOGITS
     sebagian
    0.06
     mostly
    0.06
     groep
    0.06
    Mostly
    0.06
     meanwhile
    0.06
     meantime
    0.06
     dominate
    0.06
     ebenfalls
    0.06
     Meanwhile
    0.06
     مختلفة
    0.06
    Activations Density 0.001%

    No Known Activations