© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131044
    Prev
    Next
    INDEX
    Explanations

    immobilised or driver Sebastian

    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
     llega
    -0.06
     nějak
    -0.06
    类似
    -0.06
     উহা
    -0.06
     simplement
    -0.06
    され
    -0.06
    Фор
    -0.06
     someplace
    -0.06
     каких
    -0.06
     cloths
    -0.06
    POSITIVE LOGITS
    라면
    0.06
     ketika
    0.06
     when
    0.06
    quick
    0.06
     অনুষ্ঠ
    0.05
     ಪೂರ್ವ
    0.05
     professed
    0.05
     अल्फा
    0.05
    ine
    0.05
     ignor
    0.05
    Activations Density 0.002%

    No Known Activations