© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117454
    Prev
    Next
    INDEX
    Explanations

    configuration components

    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
    として
    -0.07
     breakfast
    -0.07
     হিসাবে
    -0.06
    These
    -0.06
    They
    -0.06
    
    -0.06
     Audiobook
    -0.06
     unleashing
    -0.06
     Surprisingly
    -0.06
    getBlueTeam
    -0.06
    POSITIVE LOGITS
     associated
    0.06
     इंग
    0.06
    的的
    0.06
     dimmed
    0.05
    valid
    0.05
     在
    0.05
    ALITY
    0.05
    izziness
    0.05
    मधील
    0.05
     affiliated
    0.05
    Activations Density 0.007%

    No Known Activations