© 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. 116421
    Prev
    Next
    INDEX
    Explanations

    order, table, or dictionary structures

    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
     अशा
    -0.06
     clan
    -0.06
     deluxe
    -0.06
     wyposaż
    -0.06
     udah
    -0.06
     sebag
    -0.06
     честь
    -0.06
    뭣
    -0.06
     استاند
    -0.06
     comenzamos
    -0.05
    POSITIVE LOGITS
     akşam
    0.06
    ngày
    0.06
    modium
    0.06
     acceptable
    0.06
     الاخر
    0.06
     potrebno
    0.06
    lendir
    0.06
    পূর্বে
    0.06
     lens
    0.06
    eternal
    0.05
    Activations Density 0.032%

    No Known Activations