© 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. 119521
    Prev
    Next
    INDEX
    Explanations

    but warned

    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
     unnecessary
    -0.07
     अनावश्यक
    -0.07
     unnecessarily
    -0.07
     expenses
    -0.07
     mittlerweile
    -0.06
     expense
    -0.06
     EXC
    -0.06
     부담
    -0.06
     exceeded
    -0.06
    ケース
    -0.06
    POSITIVE LOGITS
    missing
    0.06
     отсутствие
    0.06
     missing
    0.06
     Puy
    0.06
     fehl
    0.06
     removing
    0.06
     enlarging
    0.06
     লং
    0.06
     शब्
    0.06
     szak
    0.05
    Activations Density 0.052%

    No Known Activations