© 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. 116333
    Prev
    Next
    INDEX
    Explanations

    state or county laws

    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
     الفوت
    -0.06
    україн
    -0.06
    mii
    -0.06
     концов
    -0.06
     journalism
    -0.06
     ವ್ಯವ
    -0.06
     absorbent
    -0.05
    criptor
    -0.05
    有助于
    -0.05
     auxin
    -0.05
    POSITIVE LOGITS
    вЂ
    0.06
     phường
    0.06
     variedad
    0.06
     idéale
    0.06
    вари
    0.06
     imaju
    0.06
    ahren
    0.06
     hakkında
    0.06
     erano
    0.06
     Counties
    0.06
    Activations Density 0.019%

    No Known Activations