© 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. 128840
    Prev
    Next
    INDEX
    Explanations

    organic electronics and materials

    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
     sufficiently
    -0.07
    latable
    -0.06
    这样一个
    -0.06
     regiones
    -0.06
    athe
    -0.05
     একদিন
    -0.05
     জঙ্গি
    -0.05
     prakty
    -0.05
     communicative
    -0.05
    Ꮅ
    -0.05
    POSITIVE LOGITS
    واع
    0.06
    há
    0.06
    nului
    0.06
     nw
    0.06
     zijn
    0.06
    Exceptionally
    0.06
     jsem
    0.06
    ⑅
    0.06
     rekl
    0.06
    টাকে
    0.05
    Activations Density 0.004%

    No Known Activations