© 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. 128738
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     муж
    -0.06
    when
    -0.06
     beberapa
    -0.06
     optimise
    -0.05
     terve
    -0.05
     इको
    -0.05
     defences
    -0.05
    使得
    -0.05
     this
    -0.05
     جبکہ
    -0.05
    POSITIVE LOGITS
     an
    0.07
     beautiful
    0.07
     Share
    0.06
     unseren
    0.06
     clever
    0.06
    কারীরা
    0.06
     搭
    0.06
     new
    0.06
     Marcos
    0.06
     hidden
    0.06
    Activations Density 0.000%

    No Known Activations