© 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. 116901
    Prev
    Next
    INDEX
    Explanations

    Precedential or Published

    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
    ळ
    -0.06
    iał
    -0.06
     бан
    -0.06
    шу
    -0.06
     shocking
    -0.06
     তুলনায়
    -0.06
     surpassing
    -0.06
     بہت
    -0.06
     surprisingly
    -0.06
    DISCUSSION
    -0.06
    POSITIVE LOGITS
    如此
    0.07
     美
    0.06
    sadquotes
    0.06
     대해
    0.06
     چنین
    0.06
    quisite
    0.06
     partner
    0.06
    日々
    0.06
    endent
    0.05
     bahagian
    0.05
    Activations Density 0.001%

    No Known Activations