© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 118364
    Prev
    Next
    INDEX
    Explanations

    included

    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
     could
    -0.07
     으로
    -0.06
     includes
    -0.06
     irreplaceable
    -0.06
    }=\
    -0.06
     genannt
    -0.06
    }\{
    -0.06
     each
    -0.06
     politicians
    -0.06
    ونا
    -0.06
    POSITIVE LOGITS
    特に
    0.07
    such
    0.07
    either
    0.06
    who
    0.06
     particularmente
    0.06
     obecnie
    0.06
    但在
    0.06
    方向
    0.06
     purposely
    0.06
    ;
    0.06
    Activations Density 0.004%

    No Known Activations