© 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. 130082
    Prev
    Next
    INDEX
    Explanations

    part of quality of life

    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
     shortcuts
    -0.06
    oled
    -0.06
    es
    -0.06
    ocer
    -0.05
     procrastination
    -0.05
     tomorrow
    -0.05
     जायेंगे
    -0.05
    明天
    -0.05
     கற்க
    -0.05
     বিদ্যালয়ে
    -0.05
    POSITIVE LOGITS
     having
    0.07
     상태
    0.07
     वापस
    0.07
    狀態
    0.07
     possessing
    0.07
     hoş
    0.07
     restauration
    0.06
     온도
    0.06
     njen
    0.06
     recentes
    0.06
    Activations Density 0.004%

    No Known Activations