© 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. 117063
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    :/
    -0.06
    ?
    -0.06
     hesitated
    -0.06
     их
    -0.05
     тоже
    -0.05
    Du
    -0.05
    :)
    -0.05
    :(
    -0.05
     অপূর্ব
    -0.05
    这也是
    -0.05
    POSITIVE LOGITS
    THERE
    0.07
     এখান
    0.07
    Parcel
    0.06
     সেখান
    0.06
     ruh
    0.06
     chloride
    0.06
     THERE
    0.06
     바탕
    0.06
     لہ
    0.06
     succes
    0.06
    Activations Density 0.000%

    No Known Activations