© 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. 118007
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

    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
    .
    -0.08
     some
    -0.07
    ;
    -0.06
    了一些
    -0.06
    :
    -0.06
     Some
    -0.06
    all
    -0.06
    -
    -0.06
    ko
    -0.06
    some
    -0.06
    POSITIVE LOGITS
     гимна
    0.07
     единственный
    0.07
     монасты
    0.06
    clé
    0.06
    が高い
    0.06
     incluidas
    0.06
    鈈
    0.06
     должны
    0.06
     programa
    0.06
    Tại
    0.06
    Activations Density 0.002%

    No Known Activations