© 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. 116767
    Prev
    Next
    INDEX
    Explanations

    **Prefixes of names and companies**

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ʜ
    -0.06
     discharg
    -0.06
    Iraq
    -0.06
     проти
    -0.06
     ジャケット
    -0.06
    ┝
    -0.06
    bellion
    -0.06
     hehe
    -0.06
     STATISTICS
    -0.06
     옷
    -0.06
    POSITIVE LOGITS
     cracks
    0.06
     pace
    0.06
     deven
    0.06
     přest
    0.06
    一切
    0.06
     this
    0.05
    보는
    0.05
    larla
    0.05
     cogn
    0.05
    畜
    0.05
    Activations Density 0.001%

    No Known Activations