© 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. 117587
    Prev
    Next
    INDEX
    Explanations

    names of musicians

    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
     첨
    -0.06
    actual
    -0.06
     contributed
    -0.06
     మేము
    -0.06
     crept
    -0.06
     Chart
    -0.06
    ēs
    -0.06
     ACTUAL
    -0.06
    Actual
    -0.06
     CONTRIBUTION
    -0.06
    POSITIVE LOGITS
    中心的
    0.07
    ccccc
    0.07
     বিষয়ক
    0.06
    越來越
    0.06
     increasingly
    0.06
     semaine
    0.06
    的的
    0.06
     kulland
    0.06
     ceas
    0.06
     fogl
    0.06
    Activations Density 0.014%

    No Known Activations