© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118452
    Prev
    Next
    INDEX
    Explanations

    in the

    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
     этими
    -0.06
     ছয়
    -0.06
     
    -0.06
                                   
    -0.06
    abs
    -0.05
    所需的
    -0.05
    难题
    -0.05
     প্রত্যাবর্তন
    -0.05
     just
    -0.05
    <em>
    -0.05
    POSITIVE LOGITS
     لكن
    0.07
     nhưng
    0.07
     продолжает
    0.07
    ؟
    0.07
     در
    0.07
     بیشتر
    0.07
    ずっと
    0.06
     أ
    0.06
    不斷
    0.06
    ங்களுடன்
    0.06
    Activations Density 0.003%

    No Known Activations