© 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. 116305
    Prev
    Next
    INDEX
    Explanations

    . James Nigerian Q:

    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
     முன்னே
    -0.07
    水量
    -0.06
     सदस्यों
    -0.06
    تقدم
    -0.06
     "["
    -0.06
     وهو
    -0.06
     striving
    -0.06
     commas
    -0.05
     accolades
    -0.05
    evolving
    -0.05
    POSITIVE LOGITS
     различ
    0.07
    പടി
    0.06
    icket
    0.06
    some
    0.06
    等は
    0.06
     BUS
    0.06
     kèm
    0.06
     PC
    0.06
     compartido
    0.06
     europé
    0.06
    Activations Density 0.004%

    No Known Activations