© 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. 119385
    Prev
    Next
    INDEX
    Explanations

    quotes or spoken words

    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
    ,
    -0.07
     Smith
    -0.06
    ”,
    -0.06
     some
    -0.06
     members
    -0.05
    ultimo
    -0.05
     {|
    -0.05
     Daniel
    -0.05
     results
    -0.05
     sanctuaries
    -0.05
    POSITIVE LOGITS
     अपने
    0.08
     telah
    0.07
    具有
    0.07
    旅游
    0.07
     ತನ್ನ
    0.07
    अपने
    0.07
    携带
    0.07
     GÉN
    0.06
     olid
    0.06
     possèdent
    0.06
    Activations Density 0.001%

    No Known Activations