© 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. 117060
    Prev
    Next
    INDEX
    Explanations

    movement and acceleration

    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
     sporadic
    -0.06
     jitter
    -0.06
     ramps
    -0.06
     succes
    -0.06
     Brazil
    -0.06
     pastry
    -0.06
     we
    -0.06
    賊
    -0.06
    我们
    -0.06
    \|$
    -0.06
    POSITIVE LOGITS
     오늘은
    0.06
     Их
    0.06
    發展
    0.06
     их
    0.06
     geliş
    0.06
     według
    0.06
     დღ
    0.06
    是一些
    0.06
     dzień
    0.06
     innovación
    0.06
    Activations Density 0.002%

    No Known Activations