© 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. 116327
    Prev
    Next
    INDEX
    Explanations

    energy and motion verbs

    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
     दृष्टिकोण
    -0.07
     distributional
    -0.06
    はもちろん
    -0.06
     wasser
    -0.06
     Erfahrung
    -0.06
     అదే
    -0.06
     достовер
    -0.06
    форми
    -0.05
     vulnerable
    -0.05
    麂
    -0.05
    POSITIVE LOGITS
     boost
    0.09
     boosted
    0.08
     энерги
    0.08
     energ
    0.08
     propel
    0.08
     Start
    0.08
    推动
    0.08
    boost
    0.08
     start
    0.08
     accelerate
    0.08
    Activations Density 0.068%

    No Known Activations