© 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. 118396
    Prev
    Next
    INDEX
    Explanations

    license copy

    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
     vårt
    -0.07
     existentes
    -0.06
     солне
    -0.06
    щением
    -0.06
    ©
    -0.06
     vás
    -0.06
     coordinated
    -0.06
    eluarkan
    -0.06
     uveden
    -0.06
     fabricantes
    -0.06
    POSITIVE LOGITS
     т
    0.06
     delay
    0.06
     diesen
    0.06
    作
    0.06
     ㅎ
    0.06
    veni
    0.06
     এই
    0.06
     ла
    0.06
     lol
    0.06
     ну
    0.05
    Activations Density 0.002%

    No Known Activations