© 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. 117336
    Prev
    Next
    INDEX
    Explanations

    citation suffixes

    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
     and
    -0.07
     https
    -0.07
    https
    -0.06
    ’
    -0.06
     (
    -0.06
    based
    -0.06
     فهو
    -0.06
     /
    -0.06
     आणि
    -0.06
    ানি
    -0.05
    POSITIVE LOGITS
    スタンダ
    0.07
     steamed
    0.07
     dilatation
    0.07
    ментов
    0.06
    semblance
    0.06
     primeiras
    0.06
     Бушлай
    0.06
    特效
    0.06
     স্ত্র
    0.06
     derajat
    0.06
    Activations Density 0.007%

    No Known Activations