© 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. 117169
    Prev
    Next
    INDEX
    Explanations

    nickname in quotes

    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
    ssymb
    -0.06
    ลง
    -0.06
     কেবল
    -0.06
     стали
    -0.06
     ge
    -0.06
     categoría
    -0.06
     blev
    -0.06
    categoria
    -0.06
     проти
    -0.06
    それが
    -0.06
    POSITIVE LOGITS
     சுமார்
    0.06
    ープ
    0.06
     Surprisingly
    0.06
     trakcie
    0.06
     बावजूद
    0.06
     அதே
    0.06
     hospitable
    0.06
     Basically
    0.06
    aut
    0.06
    outer
    0.06
    Activations Density 0.004%

    No Known Activations