© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130178
    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
     ngan
    -0.06
    哎
    -0.06
     எப்போதும்
    -0.06
    ſſ
    -0.06
    लास
    -0.06
     அனைவருக்கும்
    -0.05
    كلمنا
    -0.05
    唉
    -0.05
    ſ
    -0.05
     mastery
    -0.05
    POSITIVE LOGITS
     შეი
    0.06
     fonte
    0.06
     находятся
    0.06
    栊
    0.06
    方式
    0.06
    することで
    0.06
     on
    0.06
    从而
    0.06
    etition
    0.06
    pector
    0.06
    Activations Density 0.000%

    No Known Activations