© 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. 119819
    Prev
    Next
    INDEX
    Explanations

    The World of Poo

    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
     Assembl
    -0.07
     ASSEM
    -0.06
     prettiest
    -0.06
     Freude
    -0.06
    Assembly
    -0.06
     Doubt
    -0.06
     palazzo
    -0.06
     conducta
    -0.06
    ここ
    -0.06
     &.
    -0.06
    POSITIVE LOGITS
     prolonged
    0.06
     Topical
    0.06
     yra
    0.06
     অভিয
    0.05
    增加了
    0.05
     leveraged
    0.05
     calculation
    0.05
    ucha
    0.05
    background
    0.05
     absolute
    0.05
    Activations Density 0.002%

    No Known Activations