© 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. 116635
    Prev
    Next
    INDEX
    Explanations

    html div with id or class

    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
     and
    -0.06
    night
    -0.06
    frozen
    -0.05
     Wilson
    -0.05
     و
    -0.05
    edge
    -0.05
    хождения
    -0.05
     Negro
    -0.05
    find
    -0.05
     जबरदस्त
    -0.05
    POSITIVE LOGITS
     برای
    0.07
     ۴
    0.07
     proteger
    0.07
     quinto
    0.07
     pentru
    0.07
     untuk
    0.07
     ৪
    0.07
     பொதுவாக
    0.07
     Während
    0.07
     संयुक्त
    0.07
    Activations Density 0.010%

    No Known Activations