© 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. 128381
    Prev
    Next
    INDEX
    Explanations

    different [noun]

    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
     সবগুলো
    -0.09
    每一個
    -0.07
     seperti
    -0.07
     सभी
    -0.07
     deixando
    -0.07
     each
    -0.06
    每一个
    -0.06
    each
    -0.06
     соответству
    -0.06
     लाकर
    -0.06
    POSITIVE LOGITS
     zählen
    0.07
     الجزء
    0.06
    걔
    0.06
    ২৪
    0.05
     स्था
    0.05
     continuare
    0.05
     empath
    0.05
     partea
    0.05
    近年
    0.05
     primal
    0.05
    Activations Density 0.037%

    No Known Activations