© 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. 119287
    Prev
    Next
    INDEX
    Explanations

    CF types programming context

    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
     وضعیت
    -0.06
    ᵉ
    -0.06
     basalt
    -0.06
    udit
    -0.06
    conservative
    -0.06
    valo
    -0.06
     राज्यसभा
    -0.06
     judiciary
    -0.06
    純正
    -0.05
     Сле
    -0.05
    POSITIVE LOGITS
    ส่วน
    0.07
    時に
    0.06
    ashop
    0.06
    から
    0.06
    時間が
    0.06
     tienda
    0.06
     manchmal
    0.06
     this
    0.06
    Можно
    0.06
     czasem
    0.06
    Activations Density 0.003%

    No Known Activations