© 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. 130045
    Prev
    Next
    INDEX
    Explanations

    speed and time limits

    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
     HL
    -0.06
    HL
    -0.06
     significant
    -0.06
    Significant
    -0.06
     ক্লা
    -0.06
    Would
    -0.06
    waitUntil
    -0.06
     grows
    -0.05
    ūn
    -0.05
     clientele
    -0.05
    POSITIVE LOGITS
     quick
    0.07
     streamlined
    0.06
     abbrevi
    0.06
     เดิม
    0.06
     hızlı
    0.06
     objectivity
    0.06
     কোথ
    0.06
     rápidos
    0.06
    快速
    0.06
     vaak
    0.06
    Activations Density 0.033%

    No Known Activations