© 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. 129566
    Prev
    Next
    INDEX
    Explanations

    testing and repeated actions

    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
     transgender
    -0.07
     desemb
    -0.07
    専門
    -0.07
     попа
    -0.06
     ఉంది
    -0.06
     قالت
    -0.06
    转化
    -0.06
    顾客
    -0.06
    MODKEY
    -0.06
     hướng
    -0.06
    POSITIVE LOGITS
     periodic
    0.06
     of
    0.06
     başlat
    0.06
     testing
    0.06
     परीक्षण
    0.06
    測試
    0.06
     repeatedly
    0.06
     with
    0.06
     probing
    0.06
     repetitions
    0.06
    Activations Density 0.001%

    No Known Activations