© 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. 128308
    Prev
    Next
    INDEX
    Explanations

    scorewinningstreak

    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
     привод
    -0.06
     हंगामा
    -0.06
     involve
    -0.06
    vex
    -0.05
    x
    -0.05
    omotive
    -0.05
    max
    -0.05
    4
    -0.05
     Constable
    -0.05
     involuc
    -0.05
    POSITIVE LOGITS
     rye
    0.07
    禿
    0.06
    没什么
    0.06
    全部
    0.06
     margarita
    0.06
     conjunto
    0.06
     오전
    0.06
    没人
    0.06
     गृह
    0.06
    這次
    0.06
    Activations Density 0.026%

    No Known Activations