© 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. 119280
    Prev
    Next
    INDEX
    Explanations

    links and lists

    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
     ಚೆ
    -0.06
     ample
    -0.06
    itherto
    -0.06
    ঽ
    -0.06
     অবশ্য
    -0.06
    といえば
    -0.06
    不像
    -0.06
     અથવા
    -0.06
     Alternatively
    -0.06
     copious
    -0.06
    POSITIVE LOGITS
     ও
    0.07
     و
    0.07
     व
    0.06
     និង
    0.06
     ਅਤੇ
    0.06
     and
    0.06
     lahat
    0.06
    ので
    0.06
     toate
    0.06
     সবসময়
    0.06
    Activations Density 0.003%

    No Known Activations