© 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. 128463
    Prev
    Next
    INDEX
    Explanations

    listing / categorization markers

    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
     चै
    -0.08
    ✱
    -0.07
     obligations
    -0.07
     quar
    -0.07
    出す
    -0.06
     chiffres
    -0.06
    ↵↵↵↵↵↵
    -0.06
     nons
    -0.06
     obligation
    -0.06
     freaking
    -0.06
    POSITIVE LOGITS
                          
    0.07
     و
    0.06
     и
    0.06
     และ
    0.06
    7
    0.06
     및
    0.06
                                   
    0.06
     και
    0.06
     மற்றும்
    0.06
                    
    0.05
    Activations Density 0.002%

    No Known Activations