© 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. 119845
    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
    8
    -0.06
     ഭാ
    -0.06
     heed
    -0.06
     مذہب
    -0.06
    Type
    -0.06
    btn
    -0.06
     সহজে
    -0.05
    byte
    -0.05
     ಭ
    -0.05
     १५
    -0.05
    POSITIVE LOGITS
    ிலிருந்து
    0.06
     circuitos
    0.06
     çocuğ
    0.06
    东西
    0.06
     about
    0.06
     AVER
    0.06
    маш
    0.06
    introducing
    0.06
     berubah
    0.06
     propelling
    0.06
    Activations Density 0.000%

    No Known Activations