© 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. 129242
    Prev
    Next
    INDEX
    Explanations

    university, used, advice

    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
    他
    -0.07
     पांव
    -0.06
     যাবার
    -0.06
     он
    -0.06
     recieved
    -0.06
     が
    -0.06
     Received
    -0.06
     lại
    -0.06
     nib
    -0.06
    他不
    -0.06
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵↵
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    ↵↵↵↵↵↵↵↵↵
    0.06
    
    0.06
    ========
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
     requête
    0.06
    0.06
     Temmuz
    0.06
     advice
    0.06
    Activations Density 0.002%

    No Known Activations