© 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. 128494
    Prev
    Next
    INDEX
    Explanations

    email addresses and author names

    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
     un
    -0.07
     juga
    -0.06
     так
    -0.06
    但是
    -0.06
    ⁤
    -0.06
    जबकि
    -0.06
    把
    -0.06
    据悉
    -0.06
     hacer
    -0.06
     أيضا
    -0.06
    POSITIVE LOGITS
     propagator
    0.06
     reprints
    0.06
     disregarding
    0.06
     stallion
    0.06
     pertaining
    0.05
     segregated
    0.05
    ebar
    0.05
     ofrece
    0.05
    مارسة
    0.05
     two
    0.05
    Activations Density 0.009%

    No Known Activations