© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119059
    Prev
    Next
    INDEX
    Explanations

    form of technical

    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
    ﻤ
    -0.06
     една
    -0.06
     вполне
    -0.06
    )/
    -0.06
    non
    -0.06
     परीक्ष
    -0.06
    term
    -0.06
    ෝජ
    -0.06
    ずに
    -0.06
     meist
    -0.06
    POSITIVE LOGITS
    Dame
    0.07
     Dame
    0.07
     sayesinde
    0.07
    diabetes
    0.06
     sweetness
    0.06
     dame
    0.06
     นาง
    0.06
    老板
    0.06
     atherosclerosis
    0.06
     руба
    0.06
    Activations Density 0.021%

    No Known Activations