© 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. 128509
    Prev
    Next
    INDEX
    Explanations

    lengthcorrespondfunctionProduced

    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
    虽
    -0.08
    雖
    -0.07
     ihnen
    -0.07
     여러
    -0.06
     multiple
    -0.06
    ඳු
    -0.06
     Aunque
    -0.06
     entire
    -0.06
     வேண்டு
    -0.06
    หรือ
    -0.06
    POSITIVE LOGITS
     आम्ही
    0.07
     رياضيات
    0.06
     我們
    0.06
     úč
    0.06
    軽減
    0.06
     अधीक्षक
    0.05
     우리는
    0.05
     我们
    0.05
    现在
    0.05
    SystemCall
    0.05
    Activations Density 0.002%

    No Known Activations