© 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. 129023
    Prev
    Next
    INDEX
    Explanations

    Code generated by Microsoft(R) AutoRest

    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
    様の
    -0.06
     glows
    -0.06
    全部
    -0.06
     সংগ্রামের
    -0.05
     другим
    -0.05
     circled
    -0.05
     foliis
    -0.05
    さんの
    -0.05
     الساعة
    -0.05
    કલ
    -0.05
    POSITIVE LOGITS
     υψη
    0.07
     prije
    0.06
    িয়ে
    0.06
    muje
    0.06
     as
    0.06
     и
    0.06
     Questa
    0.06
    Increase
    0.06
     قبل
    0.06
    Love
    0.06
    Activations Density 0.001%

    No Known Activations