© 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. 129369
    Prev
    Next
    INDEX
    Explanations

    geodesic flow, vector bundles, tangentially connected, Stourwater, FBI director, Mate

    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
    琼
    -0.06
     adjustments
    -0.06
    瓊
    -0.06
     Tulane
    -0.06
    調節
    -0.06
     இட
    -0.06
     पूरे
    -0.06
    饵
    -0.06
     tỷ
    -0.06
     impartial
    -0.06
    POSITIVE LOGITS
     diffusion
    0.06
     strongly
    0.06
     পরিস্থিতির
    0.06
    ใกล้
    0.06
     violently
    0.06
    द्य
    0.06
     restriction
    0.05
     Dieses
    0.05
    restrictions
    0.05
     restrictions
    0.05
    Activations Density 0.001%

    No Known Activations