© 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. 117391
    Prev
    Next
    INDEX
    Explanations

    often, usually, typically

    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
     which
    -0.06
    แทน
    -0.06
    orel
    -0.06
    edia
    -0.06
    が変わ
    -0.06
            
    -0.06
     irrelevant
    -0.05
     entspricht
    -0.05
     डिवाइड
    -0.05
     แน
    -0.05
    POSITIVE LOGITS
     వి
    0.06
     days
    0.06
     splendid
    0.06
     finit
    0.06
    新たに
    0.06
     Não
    0.06
    ாய்
    0.06
     Укра
    0.06
     روز
    0.06
     нещо
    0.06
    Activations Density 0.028%

    No Known Activations