© 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. 117699
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions ending in punctuation

    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
     atyp
    -0.07
    embl
    -0.06
     nhập
    -0.06
     indicative
    -0.06
    ngo
    -0.06
     Quattro
    -0.06
    indexed
    -0.06
     conceivable
    -0.06
    の名
    -0.06
    ↳
    -0.06
    POSITIVE LOGITS
     both
    0.06
     reduz
    0.06
    uj
    0.05
     প্রয়োগ
    0.05
     reducing
    0.05
     wieder
    0.05
     BOTH
    0.05
     periodically
    0.05
     aquele
    0.05
    semos
    0.05
    Activations Density 0.003%

    No Known Activations