© 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. 116670
    Prev
    Next
    INDEX
    Explanations

    classical physics concepts

    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
    larger
    -0.06
    Passport
    -0.06
     kanssa
    -0.06
     nagyobb
    -0.06
     qualitative
    -0.06
     खून
    -0.06
     với
    -0.06
     ratios
    -0.06
    PixelRatio
    -0.06
    orsk
    -0.06
    POSITIVE LOGITS
    ഘാ
    0.06
     ancora
    0.06
     Farmers
    0.06
     මො
    0.06
     vervangen
    0.06
     ফরজ
    0.06
     परंपरागत
    0.06
     वैदिक
    0.06
    传统的
    0.06
     miền
    0.06
    Activations Density 0.002%

    No Known Activations