© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118783
    Prev
    Next
    INDEX
    Explanations

    copyright notices in code

    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
    が
    -0.07
    വീ
    -0.06
     Pray
    -0.06
    近年
    -0.06
     Hace
    -0.06
     на
    -0.06
     diary
    -0.06
     місце
    -0.06
    Till
    -0.06
     abbiamo
    -0.05
    POSITIVE LOGITS
    NODE
    0.06
     这个
    0.06
    kbd
    0.06
    keycode
    0.06
     प्रस्ताव
    0.06
    ked
    0.06
    circled
    0.06
    ሙሉ
    0.06
     пят
    0.06
     seawater
    0.06
    Activations Density 0.002%

    No Known Activations