© 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. 129459
    Prev
    Next
    INDEX
    Explanations

    List titles or headings

    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
     neighborhood
    -0.06
     neighbourhood
    -0.06
     மாசுபாடு
    -0.06
    iquity
    -0.06
     pulp
    -0.06
    bursement
    -0.06
    accessibility
    -0.06
     sirf
    -0.06
    ликт
    -0.06
    ♕
    -0.06
    POSITIVE LOGITS
     kú
    0.07
     their
    0.07
     основной
    0.07
     उनकी
    0.06
    他们的
    0.06
    हरूको
    0.06
     learn
    0.06
     основ
    0.06
     background
    0.06
    それぞれの
    0.06
    Activations Density 0.006%

    No Known Activations