© 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. 130991
    Prev
    Next
    INDEX
    Explanations

    mucosal antigen, hepatic accumulation, secretory piece, Eat grapes

    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
     compulsive
    -0.06
    🤑
    -0.06
     fährt
    -0.06
     burnout
    -0.06
    ronym
    -0.06
     calories
    -0.06
    ণি
    -0.06
     torque
    -0.06
     أنا
    -0.06
     पुस्तक
    -0.05
    POSITIVE LOGITS
     protection
    0.08
    Protection
    0.07
    protection
    0.07
     Protection
    0.06
     protección
    0.06
    layered
    0.06
     protecting
    0.06
     当
    0.06
     protector
    0.06
    Defence
    0.06
    Activations Density 0.015%

    No Known Activations