© 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. 128936
    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
     Subsequent
    -0.07
     केवळ
    -0.06
     فقط
    -0.06
     solely
    -0.06
    際の
    -0.06
     only
    -0.06
     despite
    -0.06
    mund
    -0.06
     Despite
    -0.06
     со
    -0.06
    POSITIVE LOGITS
    stige
    0.06
     깜
    0.06
    來到
    0.06
    leve
    0.05
    給你
    0.05
     pept
    0.05
     sidste
    0.05
    级别
    0.05
     EL
    0.05
    极
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.