© 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. 120124
    Prev
    Next
    INDEX
    Explanations

    numbers and currency codes

    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
     zwei
    -0.06
     tambien
    -0.06
     drei
    -0.06
     also
    -0.06
    helves
    -0.06
    біль
    -0.06
    สอง
    -0.06
     এছাড়াও
    -0.06
     amistad
    -0.05
     যোদ্ধা
    -0.05
    POSITIVE LOGITS
    လေး
    0.06
     seus
    0.06
     pouvez
    0.06
    Inflater
    0.06
    ابعه
    0.06
     quand
    0.06
    गति
    0.06
     acceder
    0.05
    áll
    0.05
     માહિતી
    0.05
    Activations Density 0.001%

    No Known Activations