© 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. 117646
    Prev
    Next
    INDEX
    Explanations

    programming syntax

    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
     tránh
    -0.06
    get
    -0.06
     საჭ
    -0.06
     то
    -0.05
     goede
    -0.05
     quando
    -0.05
    izioni
    -0.05
     menghindari
    -0.05
     East
    -0.05
    quest
    -0.05
    POSITIVE LOGITS
     aswell
    0.06
     ebenfalls
    0.06
    <eos>
    0.06
    Yes
    0.06
     Namib
    0.06
    𝕐
    0.06
     också
    0.06
     Namibia
    0.06
     આવ્યું
    0.05
    ummers
    0.05
    Activations Density 0.001%

    No Known Activations