© 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. 118545
    Prev
    Next
    INDEX
    Explanations

    ]{

    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
    This
    -0.06
    这
    -0.06
    buzz
    -0.06
     也
    -0.06
     flux
    -0.06
    0
    -0.06
     loss
    -0.05
    十
    -0.05
    Highly
    -0.05
     gate
    -0.05
    POSITIVE LOGITS
     decipher
    0.08
     الحصول
    0.07
     namens
    0.07
     Premises
    0.07
     ispir
    0.06
    诠
    0.06
    ………………………………
    0.06
     ();
    0.06
     zonder
    0.06
    после
    0.06
    Activations Density 0.002%

    No Known Activations