© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130811
    Prev
    Next
    INDEX
    Explanations

    et al

    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
     ఉపయోగ
    -0.07
    MODEL
    -0.06
     الحالي
    -0.06
    ologo
    -0.06
    ાડ
    -0.06
     utilizados
    -0.06
     MODEL
    -0.06
     ప్రస్తు
    -0.06
    Used
    -0.06
     aquela
    -0.06
    POSITIVE LOGITS
     unregistered
    0.08
    locally
    0.07
     locally
    0.06
     Event
    0.06
    ↵↵↵↵↵
    0.06
     anbieten
    0.06
     torrential
    0.06
     любые
    0.05
    ActivityResult
    0.05
     nine
    0.05
    Activations Density 0.004%

    No Known Activations