© 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. 116283
    Prev
    Next
    INDEX
    Explanations

    CheckInFragment.java

    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
     commodities
    -0.08
     তিন
    -0.08
    commodity
    -0.07
     هڪ
    -0.07
     percentages
    -0.07
     aggregates
    -0.06
     మీద
    -0.06
    mment
    -0.06
     essences
    -0.06
     तीन
    -0.06
    POSITIVE LOGITS
     lifelong
    0.07
    astro
    0.06
    ,
    0.06
    cl
    0.06
    DSL
    0.06
     розді
    0.06
    ),
    0.06
     apiClient
    0.06
    ",
    0.06
     名前
    0.06
    Activations Density 0.001%

    No Known Activations