© 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. 128831
    Prev
    Next
    INDEX
    Explanations

    anniversary of

    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
     shortly
    -0.06
    தே
    -0.06
     ক্ষুধার
    -0.06
     honestly
    -0.06
     propriété
    -0.06
     semplicemente
    -0.06
     under
    -0.06
     employees
    -0.05
    ุ่ง
    -0.05
    和其他
    -0.05
    POSITIVE LOGITS
    要有
    0.07
     zawier
    0.07
     avoiding
    0.07
     minimising
    0.06
    णसी
    0.06
     Malaysia
    0.06
     laissé
    0.06
     ഇങ്ങനെ
    0.06
     בד
    0.06
     พร้อม
    0.06
    Activations Density 0.010%

    No Known Activations