© 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. 116426
    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
    avacan
    -0.06
     friendliness
    -0.06
    ட்ப
    -0.06
    blockSize
    -0.06
     beginnen
    -0.06
    anske
    -0.06
     भाई
    -0.06
    无疑
    -0.06
     friend
    -0.05
    ocèle
    -0.05
    POSITIVE LOGITS
     refuse
    0.07
     whereas
    0.06
     sürekli
    0.06
     steeds
    0.06
     constantemente
    0.06
     refused
    0.06
     durante
    0.06
    ⇄
    0.06
     always
    0.06
     Whereas
    0.06
    Activations Density 0.000%

    No Known Activations