© 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. 119470
    Prev
    Next
    INDEX
    Explanations

    archive tags

    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
     three
    -0.06
    jad
    -0.06
    adım
    -0.05
     this
    -0.05
    我现在
    -0.05
     ಕಾರಣ
    -0.05
     ਕੁ
    -0.05
    三個
    -0.05
     six
    -0.05
     some
    -0.05
    POSITIVE LOGITS
    越来越
    0.07
     publicados
    0.06
    شتی
    0.06
     क्लो
    0.06
     используются
    0.06
     использует
    0.06
    越來越
    0.06
     colocando
    0.06
    گا
    0.06
    маш
    0.06
    Activations Density 0.051%

    No Known Activations