© 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. 118858
    Prev
    Next
    INDEX
    Explanations

    performance was disappointing

    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
     недоста
    -0.08
     handicap
    -0.07
     melaksanakan
    -0.07
     thiếu
    -0.07
    ก็ตาม
    -0.06
    overty
    -0.06
     manque
    -0.06
     تنفيذ
    -0.06
     نقص
    -0.06
     habit
    -0.06
    POSITIVE LOGITS
     rumoured
    0.06
     shrouded
    0.06
     только
    0.06
     zupeł
    0.06
     tylko
    0.06
     더욱
    0.06
    全新的
    0.06
     যিনি
    0.06
    ڀ
    0.06
     хотя
    0.06
    Activations Density 0.022%

    No Known Activations