© 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. 117530
    Prev
    Next
    INDEX
    Explanations

    puzzle pieces

    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
    sequence
    -0.06
    driven
    -0.06
     utilisée
    -0.06
     વે
    -0.06
     transports
    -0.06
     driven
    -0.06
     jakości
    -0.06
    尊
    -0.06
    地位
    -0.06
     često
    -0.06
    POSITIVE LOGITS
     fragment
    0.08
     surrounding
    0.08
    拼接
    0.07
     Puzzle
    0.07
     remainder
    0.07
     prevented
    0.07
     jigsaw
    0.07
     puzzle
    0.07
     фраг
    0.06
     gradual
    0.06
    Activations Density 0.005%

    No Known Activations