© 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. 130659
    Prev
    Next
    INDEX
    Explanations

    Various types of

    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
    对其
    -0.08
    主要
    -0.06
     separate
    -0.06
     notable
    -0.06
     während
    -0.06
     significant
    -0.06
     developing
    -0.05
     अलविदा
    -0.05
    ளான
    -0.05
     unique
    -0.05
    POSITIVE LOGITS
     OTHER
    0.07
     BECAUSE
    0.07
    tiket
    0.06
     elephants
    0.06
     ঈশ্বরের
    0.06
    电设备
    0.06
    ooq
    0.06
     Acting
    0.06
    Indeed
    0.06
     slid
    0.06
    Activations Density 0.022%

    No Known Activations