© 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. 128877
    Prev
    Next
    INDEX
    Explanations

    database keys id FK pk

    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
     wybor
    -0.06
     தோட்ட
    -0.06
     scarred
    -0.06
    σιμοποι
    -0.06
    尽量
    -0.06
     постара
    -0.06
    året
    -0.06
    當年
    -0.06
     heut
    -0.06
    ouk
    -0.06
    POSITIVE LOGITS
     marketing
    0.06
     refer
    0.06
     وليس
    0.06
     REFER
    0.06
     validated
    0.05
     ست
    0.05
    REFER
    0.05
     بخش
    0.05
     tenemos
    0.05
    大型
    0.05
    Activations Density 0.002%

    No Known Activations