© 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. 120340
    Prev
    Next
    INDEX
    Explanations

    specific names and entities

    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
     largely
    -0.06
    Several
    -0.06
    If
    -0.06
    According
    -0.06
    within
    -0.06
    由于
    -0.06
     reminiscent
    -0.06
     частично
    -0.06
    歡迎
    -0.06
    also
    -0.06
    POSITIVE LOGITS
     debes
    0.07
     RANK
    0.07
     عشق
    0.06
     standardize
    0.06
     reikia
    0.06
     sudd
    0.06
    oust
    0.06
     especie
    0.06
     einzelne
    0.06
     אחר
    0.06
    Activations Density 0.004%

    No Known Activations