© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130617
    Prev
    Next
    INDEX
    Explanations

    as always, you are free

    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
     lately
    -0.06
     Lately
    -0.06
     periodically
    -0.06
     -
    -0.06
     காலம்
    -0.06
     外
    -0.06
    Group
    -0.05
     иметь
    -0.05
    venture
    -0.05
    globals
    -0.05
    POSITIVE LOGITS
     sông
    0.07
     nuest
    0.07
     معه
    0.07
    ところ
    0.06
     exemplu
    0.06
     результате
    0.06
     nuestra
    0.06
    AddField
    0.06
     इनसे
    0.06
     cientos
    0.06
    Activations Density 0.013%

    No Known Activations