© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 120625
    Prev
    Next
    INDEX
    Explanations

    language codes, German, NEW YORK

    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
    வதால்
    -0.06
    ijoje
    -0.06
    ^{+}$
    -0.06
     term
    -0.06
    伝える
    -0.06
     potere
    -0.06
     value
    -0.06
     Р
    -0.05
     در
    -0.05
     inj
    -0.05
    POSITIVE LOGITS
    以及
    0.06
    幾乎
    0.06
     ध्वस्त
    0.06
    はもちろん
    0.06
     Шрифт
    0.06
     दोषियों
    0.06
    甚至
    0.06
     grundsätzlich
    0.06
    should
    0.06
    例如
    0.06
    Activations Density 0.001%

    No Known Activations