© 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. 117172
    Prev
    Next
    INDEX
    Explanations

    in sentence

    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
     பயன்ப
    -0.07
     기본적인
    -0.07
     አንድ
    -0.07
    經常
    -0.07
    週
    -0.07
    经常
    -0.06
     තම
    -0.06
    そこに
    -0.06
     Paket
    -0.06
     तीन
    -0.06
    POSITIVE LOGITS
    ann
    0.06
    句
    0.06
    前者
    0.05
    可
    0.05
     ?
    0.05
     competence
    0.05
     spokes
    0.05
     Ch
    0.05
     differs
    0.05
     W
    0.05
    Activations Density 0.023%

    No Known Activations