© 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. 120692
    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
     seu
    -0.07
    品牌的
    -0.07
    就算是
    -0.06
     inconvén
    -0.06
     poros
    -0.06
     üzerinden
    -0.06
    雰囲気
    -0.06
     Moreover
    -0.06
    Moreover
    -0.06
    érez
    -0.06
    POSITIVE LOGITS
    ，
    0.06
    。
    0.06
     efectivamente
    0.06
     to
    0.06
     마
    0.05
    長
    0.05
     மா
    0.05
    ：
    0.05
    /%
    0.05
    nego
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.