© 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. 119602
    Prev
    Next
    INDEX
    Explanations

    SendMessage or WM Message

    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
     accompany
    -0.07
     ഉത്സവ
    -0.06
     these
    -0.06
    公安
    -0.06
     steroids
    -0.06
    ेटेड
    -0.06
     epidemiology
    -0.06
    rapie
    -0.06
     testosterone
    -0.06
    必ず
    -0.06
    POSITIVE LOGITS
     receb
    0.07
     received
    0.06
    received
    0.06
     ma
    0.06
    attempt
    0.06
     may
    0.06
    很多的
    0.06
    SPECIAL
    0.05
     rebut
    0.05
    Special
    0.05
    Activations Density 0.002%

    No Known Activations