© 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. 116308
    Prev
    Next
    INDEX
    Explanations

    online editing

    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
     更
    -0.06
     ইতো
    -0.06
     zeer
    -0.06
     তোর
    -0.06
    用户的
    -0.06
     Dein
    -0.06
     উপরের
    -0.06
     Corresponding
    -0.06
    <0x1D>
    -0.06
     другой
    -0.05
    POSITIVE LOGITS
    Apakah
    0.06
     opium
    0.06
     ভোটে
    0.06
     đoạn
    0.06
    around
    0.06
     wattage
    0.06
     omnichannel
    0.05
     around
    0.05
     gets
    0.05
    UpdateChoice
    0.05
    Activations Density 0.001%

    No Known Activations