© 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. 120493
    Prev
    Next
    INDEX
    Explanations

    second derivative,nabla,delta

    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
     standen
    -0.07
     dvě
    -0.07
    加入
    -0.07
     অথবা
    -0.07
    参加
    -0.06
     செயல்பா
    -0.06
    または
    -0.06
     ensuring
    -0.06
    午前
    -0.06
     tenemos
    -0.06
    POSITIVE LOGITS
     preguntar
    0.06
     ফেল
    0.06
    Practical
    0.06
     পায়ের
    0.05
    Well
    0.05
    enay
    0.05
     오히려
    0.05
     reput
    0.05
     practical
    0.05
     طبعا
    0.05
    Activations Density 0.002%

    No Known Activations