© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118936
    Prev
    Next
    INDEX
    Explanations

    rotten chunk, Poké Ball, Villa, Monday, Panthers

    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
     CODE
    -0.06
    WILL
    -0.06
     possibly
    -0.06
    💼
    -0.06
     kawasan
    -0.06
    possibly
    -0.06
     enthous
    -0.06
     MAXIMUM
    -0.05
    strcpy
    -0.05
    argv
    -0.05
    POSITIVE LOGITS
    Además
    0.06
     माउंट
    0.06
     মৌলিক
    0.06
    各大
    0.06
     ยัง
    0.06
     surfacing
    0.06
     பல்வேறு
    0.06
     Dö
    0.06
     foundational
    0.06
     แทน
    0.06
    Activations Density 0.004%

    No Known Activations