© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 116566
    Prev
    Next
    INDEX
    Explanations

    Grant Thornton

    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
     both
    -0.07
     উভয়
    -0.06
     Pfizer
    -0.06
     পরীক্ষায়
    -0.06
    both
    -0.06
     চেয়ে
    -0.06
     主要
    -0.06
    忝
    -0.05
    Both
    -0.05
     cả
    -0.05
    POSITIVE LOGITS
    uestos
    0.07
     dva
    0.07
     два
    0.07
     возможность
    0.07
     affront
    0.06
     алыңыз
    0.06
     замеча
    0.06
     commotion
    0.06
     elegante
    0.06
    año
    0.06
    Activations Density 0.001%

    No Known Activations