© 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. 120308
    Prev
    Next
    INDEX
    Explanations

    different options, next page, delete student, initial option

    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
    납
    -0.06
    ő
    -0.05
     vanligt
    -0.05
    买了
    -0.05
     प्रतिक्रिया
    -0.05
     sequence
    -0.05
    ^{-}\
    -0.05
     silicon
    -0.05
    스러운
    -0.05
    Close
    -0.05
    POSITIVE LOGITS
     чему
    0.07
     quella
    0.07
    \},
    0.07
     riqueza
    0.06
     nuova
    0.06
    
    0.06
     Concerns
    0.06
     tentang
    0.06
     aquela
    0.06
     hopes
    0.06
    Activations Density 0.001%

    No Known Activations