© 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. 116337
    Prev
    Next
    INDEX
    Explanations

    already purchased or enrolled

    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
     firefighter
    -0.07
     corrispond
    -0.06
     části
    -0.06
    bie
    -0.06
     compromises
    -0.06
    corresponding
    -0.06
     putative
    -0.05
     ditetapkan
    -0.05
     hypotheses
    -0.05
    ทั้ง
    -0.05
    POSITIVE LOGITS
     reen
    0.06
     ubuntu
    0.06
    updated
    0.06
    🆙
    0.06
     revisit
    0.06
     annexation
    0.06
     revisiting
    0.06
     без
    0.06
     توسعه
    0.06
     utan
    0.06
    Activations Density 0.004%

    No Known Activations