© 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. 128845
    Prev
    Next
    INDEX
    Explanations

    cities, places, rankings, hubs

    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
     they
    -0.07
     они
    -0.07
     legnagyobb
    -0.07
     deniz
    -0.07
     большие
    -0.07
     suur
    -0.07
     විශ
    -0.06
     крупней
    -0.06
    বিহীন
    -0.06
     technologists
    -0.06
    POSITIVE LOGITS
    esehatan
    0.06
    卫
    0.06
     dimana
    0.06
    幸福
    0.06
     where
    0.06
    где
    0.06
    சா
    0.06
     mutlu
    0.06
     ആരോഗ്യ
    0.06
    春
    0.05
    Activations Density 0.010%

    No Known Activations