© 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. 129280
    Prev
    Next
    INDEX
    Explanations

    email headers

    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
     আদ
    -0.06
    在该
    -0.06
     difficulty
    -0.05
     ";
    -0.05
    <0x8E>
    -0.05
    <0x93>
    -0.05
    dealing
    -0.05
    、
    -0.05
     belated
    -0.05
     participating
    -0.05
    POSITIVE LOGITS
     результаты
    0.06
     fantastical
    0.06
     পৃষ্ঠা
    0.06
    வற்றை
    0.06
    故意
    0.06
     normales
    0.06
     laatste
    0.06
     horr
    0.06
     satte
    0.06
    有些
    0.06
    Activations Density 0.004%

    No Known Activations