© 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. 116907
    Prev
    Next
    INDEX
    Explanations

    angular.module dependencies

    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
    比如說
    -0.06
     superb
    -0.06
     catalyze
    -0.06
    trong
    -0.06
    ওয়ে
    -0.06
    धर
    -0.06
    르게
    -0.06
    SOME
    -0.06
    মধ্যে
    -0.06
    GREAT
    -0.06
    POSITIVE LOGITS
    雖然
    0.06
     thing
    0.06
    Ἱ
    0.06
     наличие
    0.06
     도움
    0.06
     courts
    0.06
     আমি
    0.06
     उपस्थिति
    0.06
     наличии
    0.05
    adım
    0.05
    Activations Density 0.001%

    No Known Activations