© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118314
    Prev
    Next
    INDEX
    Explanations

    in motion or controlled states

    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
    だけ
    -0.06
     discrete
    -0.06
     lì
    -0.06
     क्लिक
    -0.06
     поведение
    -0.06
     PLEASE
    -0.06
     structures
    -0.05
     behaviour
    -0.05
     delanter
    -0.05
     twitter
    -0.05
    POSITIVE LOGITS
    竣工
    0.07
    pipeline
    0.07
     analogous
    0.06
    rescue
    0.06
     oftentimes
    0.06
     آنا
    0.06
    通用
    0.06
     innym
    0.06
     difference
    0.06
     служба
    0.06
    Activations Density 0.013%

    No Known Activations