© 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. 117709
    Prev
    Next
    INDEX
    Explanations

    module, app, bundle

    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
    ชนิด
    -0.06
    討
    -0.06
    讨厌
    -0.06
    車種
    -0.06
     selfless
    -0.06
    type
    -0.06
    了一种
    -0.06
    exists
    -0.06
    эф
    -0.06
     guidebook
    -0.06
    POSITIVE LOGITS
    觀察
    0.06
     امریکی
    0.06
    ?!
    0.06
     মার্কিন
    0.06
    等
    0.06
    微微
    0.06
     অবস্থান
    0.06
    }]$,
    0.06
    略
    0.06
     ज्व
    0.06
    Activations Density 0.006%

    No Known Activations