© 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. 118301
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
     원하는
    -0.08
     prefers
    -0.08
     preferable
    -0.08
     suggests
    -0.08
     memilih
    -0.07
     বিভিন্ন
    -0.07
     prefer
    -0.07
     preferencia
    -0.07
     brings
    -0.07
     delivers
    -0.07
    POSITIVE LOGITS
    .
    0.06
    G
    0.06
    c
    0.06
    L
    0.06
    co
    0.06
    Ter
    0.05
    Bian
    0.05
    bian
    0.05
    ig
    0.05
    M
    0.05
    Activations Density 0.001%

    No Known Activations