© 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. 119546
    Prev
    Next
    INDEX
    Explanations

    skip over

    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
     ještě
    -0.06
     noch
    -0.06
    hasht
    -0.06
     верну
    -0.05
     asks
    -0.05
     convenient
    -0.05
     previously
    -0.05
    स्ताना
    -0.05
    ArrivalTime
    -0.05
     गाँव
    -0.05
    POSITIVE LOGITS
     những
    0.07
    setShow
    0.06
     descendants
    0.06
    обходимо
    0.06
     mercado
    0.06
    evin
    0.06
     Daunting
    0.06
    다면
    0.06
     obstáculos
    0.06
    气
    0.06
    Activations Density 0.001%

    No Known Activations