© 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. 118304
    Prev
    Next
    INDEX
    Explanations

    axial, radial, longitudinal, vertical directions

    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
    உங்கள்
    -0.06
    oult
    -0.06
     Proced
    -0.06
     умолчанию
    -0.06
    通常
    -0.06
    最好
    -0.06
     alcanzar
    -0.06
    chip
    -0.06
     gewählt
    -0.06
    operasi
    -0.06
    POSITIVE LOGITS
     by
    0.08
    由
    0.07
     substitute
    0.06
     вариант
    0.06
     souvenirs
    0.06
     копия
    0.06
     three
    0.06
     among
    0.06
     შორის
    0.06
     由
    0.06
    Activations Density 0.006%

    No Known Activations