© 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. 117590
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames

    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
    因为
    -0.06
     receivables
    -0.06
    向下
    -0.06
    reachable
    -0.05
    ຈາກ
    -0.05
    ipak
    -0.05
    принима
    -0.05
    浅
    -0.05
    ন্যা
    -0.05
    }}^{
    -0.05
    POSITIVE LOGITS
     tambien
    0.07
     भी
    0.06
     dimana
    0.06
     والله
    0.06
     meines
    0.06
     peut
    0.06
    FONT
    0.06
    我們先
    0.05
    ദാ
    0.05
     тоже
    0.05
    Activations Density 0.018%

    No Known Activations