© 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. 120128
    Prev
    Next
    INDEX
    Explanations

    arthropods and crustaceans

    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
     dla
    -0.07
     célèbre
    -0.07
    或其他
    -0.06
    ართველ
    -0.06
     distro
    -0.06
     květ
    -0.06
     analysing
    -0.06
     ফো
    -0.06
     mails
    -0.06
     primera
    -0.06
    POSITIVE LOGITS
    ရား
    0.06
     storage
    0.06
     rollover
    0.06
     Tornado
    0.05
     longing
    0.05
     skyscrapers
    0.05
     croissant
    0.05
     يصير
    0.05
     status
    0.05
     chopping
    0.05
    Activations Density 0.009%

    No Known Activations