© 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. 120083
    Prev
    Next
    INDEX
    Explanations

    news headlines and organizations

    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
     поезд
    -0.08
     soutien
    -0.06
    れている
    -0.06
     लोकांना
    -0.06
     उस
    -0.06
     hjust
    -0.06
     sledge
    -0.06
     apoio
    -0.05
     a
    -0.05
    ujjati
    -0.05
    POSITIVE LOGITS
     همین
    0.06
                     
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
                      
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    统一
    0.06
     invece
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    Activations Density 0.005%

    No Known Activations