© 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. 131063
    Prev
    Next
    INDEX
    Explanations

    Q: or Pre-

    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
     பிற
    -0.07
    倚
    -0.06
     weitere
    -0.06
     mohabbat
    -0.06
    Weitere
    -0.06
    旺
    -0.06
     aceasta
    -0.06
    ക്കിയ
    -0.05
     result
    -0.05
     indoor
    -0.05
    POSITIVE LOGITS
    おく
    0.06
     panicked
    0.06
     moths
    0.06
     destiné
    0.06
    অপ
    0.06
     preferable
    0.06
     clums
    0.06
     needed
    0.06
     IMMEDI
    0.06
     pasir
    0.05
    Activations Density 0.001%

    No Known Activations