© 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. 118812
    Prev
    Next
    INDEX
    Explanations

    SCC workability, Moms, means

    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
     ski
    -0.06
     And
    -0.06
     विभागा
    -0.05
    ثم
    -0.05
     Raised
    -0.05
    PH
    -0.05
    Process
    -0.05
     Stunning
    -0.05
     []
    -0.05
     went
    -0.05
    POSITIVE LOGITS
     isto
    0.08
    登记
    0.06
     límite
    0.06
     paździer
    0.06
     Theory
    0.06
     შეიძლება
    0.06
     cercare
    0.06
    ေသ
    0.06
    己
    0.06
     blij
    0.06
    Activations Density 0.001%

    No Known Activations