© 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. 128576
    Prev
    Next
    INDEX
    Explanations

    product or item

    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
     counselors
    -0.06
     солнца
    -0.06
     apprehensive
    -0.06
    ǿ
    -0.06
     accesses
    -0.06
     surfer
    -0.06
     Karten
    -0.06
     counsell
    -0.05
     computable
    -0.05
    ǔ
    -0.05
    POSITIVE LOGITS
    商品
    0.08
     পণ্য
    0.08
     제품
    0.08
     proizvođa
    0.08
    物品
    0.07
    货
    0.07
     market
    0.07
    貨
    0.07
     මිල
    0.07
     commodity
    0.07
    Activations Density 0.024%

    No Known Activations