© 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. 120149
    Prev
    Next
    INDEX
    Explanations

    census and tournament years

    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
     মাঝে
    -0.07
     ১৪
    -0.07
     శి
    -0.06
    中间
    -0.06
     ahí
    -0.06
    之中
    -0.06
    सेप्ट
    -0.06
    личе
    -0.06
    无数
    -0.06
     পুরস্কার
    -0.06
    POSITIVE LOGITS
    などの
    0.07
    profile
    0.06
     وغیرہ
    0.06
    等の
    0.06
    కుల
    0.06
    等
    0.06
     wacky
    0.06
     remnants
    0.05
     VECTOR
    0.05
    Prof
    0.05
    Activations Density 0.001%

    No Known Activations