© 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. 128737
    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
     aplik
    -0.06
     Orwell
    -0.06
     memastikan
    -0.06
     permettant
    -0.06
     পালিয়ে
    -0.05
    什么样的
    -0.05
    論文
    -0.05
    =[-
    -0.05
     बहस
    -0.05
    确保
    -0.05
    POSITIVE LOGITS
     پیروی
    0.07
     കാരണം
    0.07
     Although
    0.06
    方面的
    0.06
     devoted
    0.06
     devoting
    0.06
    Similar
    0.06
    మూ
    0.06
    RunWith
    0.06
     labai
    0.06
    Activations Density 0.000%

    No Known Activations