© 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. 120220
    Prev
    Next
    INDEX
    Explanations

    home, college, india, bathroom, short course

    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
    Moreover
    -0.07
    ause
    -0.06
     Moreover
    -0.06
     massively
    -0.06
    ङ्
    -0.06
    很多
    -0.06
    adah
    -0.06
     mainly
    -0.06
     DR
    -0.06
     you
    -0.06
    POSITIVE LOGITS
    ไม่
    0.08
     keine
    0.07
    stitial
    0.06
     receive
    0.06
     केरल
    0.06
     ontvangen
    0.06
     моих
    0.06
     реконструк
    0.06
     جاي
    0.06
     одна
    0.06
    Activations Density 0.027%

    No Known Activations