© 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. 116839
    Prev
    Next
    INDEX
    Explanations

    undefined data or code fragments

    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
    但是
    -0.06
    ]
    -0.06
    umb
    -0.06
    *
    -0.06
     nonetheless
    -0.06
    est
    -0.06
     but
    -0.05
     nevertheless
    -0.05
    II
    -0.05
    )
    -0.05
    POSITIVE LOGITS
     옵
    0.07
    ിലാണ്
    0.07
     используя
    0.06
     بالإ
    0.06
     বাংলাদেশ
    0.06
    >≥</
    0.06
    쾨
    0.06
     microbial
    0.06
     Nationale
    0.06
     ดี
    0.06
    Activations Density 0.008%

    No Known Activations