© 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. 119452
    Prev
    Next
    INDEX
    Explanations

    diverse biological effects

    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
     사용할
    -0.08
     использовать
    -0.08
     homemade
    -0.07
     사용
    -0.07
     utilizar
    -0.07
     القيام
    -0.07
     тези
    -0.07
    初步
    -0.07
     reasonably
    -0.07
     pengguna
    -0.07
    POSITIVE LOGITS
    2
    0.06
     sejumlah
    0.06
     flo
    0.06
    Shirts
    0.06
     худ
    0.05
     diversa
    0.05
    kjhtml
    0.05
     tantas
    0.05
     diverso
    0.05
     दुसरे
    0.05
    Activations Density 0.009%

    No Known Activations