© 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. 119738
    Prev
    Next
    INDEX
    Explanations

    functional modifications and additives

    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
     inspired
    -0.07
     combining
    -0.07
     combines
    -0.07
     innov
    -0.06
    chedule
    -0.06
     eligible
    -0.06
     innovative
    -0.06
    inspired
    -0.06
     resourceful
    -0.05
    combine
    -0.05
    POSITIVE LOGITS
    Analysis
    0.07
     stabilizes
    0.06
    Analyzer
    0.06
    ındadır
    0.06
    Attempts
    0.06
     характери
    0.06
     пытается
    0.06
    stabil
    0.06
    ुआ
    0.06
     estabilidad
    0.06
    Activations Density 0.010%

    No Known Activations