© 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. 128403
    Prev
    Next
    INDEX
    Explanations

    committed to, use, similar, check, All

    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
     this
    -0.09
     two
    -0.07
     tomto
    -0.06
    这一
    -0.06
     недостатки
    -0.06
     THIS
    -0.06
     এই
    -0.06
    this
    -0.06
     risultati
    -0.06
     dieses
    -0.06
    POSITIVE LOGITS
    例如
    0.07
     esimerkiksi
    0.07
     například
    0.06
     appare
    0.06
     например
    0.06
     misalnya
    0.06
     bijvoorbeeld
    0.06
    ଲ
    0.06
     according
    0.06
    According
    0.06
    Activations Density 0.003%

    No Known Activations