© 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. 116870
    Prev
    Next
    INDEX
    Explanations

    head tag, Q:, why you

    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
    separate
    -0.06
     separate
    -0.06
     zusätz
    -0.06
     vem
    -0.06
     menemukan
    -0.06
     zusätzlichen
    -0.06
     καλύτε
    -0.06
    nější
    -0.06
     cancelling
    -0.06
     encontrará
    -0.06
    POSITIVE LOGITS
    そして
    0.07
    вичай
    0.06
    以
    0.06
     обы
    0.06
    Sql
    0.06
    人は
    0.06
    defl
    0.05
    今
    0.05
    च्
    0.05
     norma
    0.05
    Activations Density 0.001%

    No Known Activations