© 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. 130314
    Prev
    Next
    INDEX
    Explanations

    Q: followed by text

    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
     so
    -0.06
     other
    -0.06
    bv
    -0.06
     and
    -0.05
    many
    -0.05
     कार
    -0.05
    ன்றி
    -0.05
     Some
    -0.05
     necessárias
    -0.05
     রোড
    -0.05
    POSITIVE LOGITS
     außergewöhn
    0.07
     Sasaki
    0.06
     comedian
    0.06
    🌿
    0.06
    
    0.06
     LISTEN
    0.06
     ribbed
    0.06
     कॉमे
    0.06
     包括
    0.06
     seashell
    0.06
    Activations Density 0.001%

    No Known Activations