© 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. 129614
    Prev
    Next
    INDEX
    Explanations

    require("./swarm")

    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
     movement
    -0.07
     mover
    -0.06
    movement
    -0.06
    moved
    -0.06
     múltiplos
    -0.06
     but
    -0.06
    intervals
    -0.06
    فيق
    -0.06
    bewegung
    -0.06
    얘
    -0.06
    POSITIVE LOGITS
     calculated
    0.08
    ocard
    0.07
     vykon
    0.07
     calculations
    0.06
    calculated
    0.06
     calculado
    0.06
     নমুনা
    0.06
    гідно
    0.06
    不足
    0.06
     calculating
    0.06
    Activations Density 0.001%

    No Known Activations