© 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. 117051
    Prev
    Next
    INDEX
    Explanations

    \

    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
     شما
    -0.08
     আপনি
    -0.07
    您
    -0.07
    hrte
    -0.06
    Listed
    -0.06
    编号
    -0.06
     jste
    -0.06
    Ũ
    -0.06
     syst
    -0.06
     você
    -0.06
    POSITIVE LOGITS
     their
    0.06
     his
    0.06
     lehet
    0.06
     மகிழ்ச்ச
    0.06
    rt
    0.06
    exec
    0.06
     all
    0.06
    if
    0.06
     wajib
    0.05
     just
    0.05
    Activations Density 0.001%

    No Known Activations