© 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. 130760
    Prev
    Next
    INDEX
    Explanations

    second instance or following number

    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
     disrespectful
    -0.07
     계속
    -0.07
    adece
    -0.06
    σκεται
    -0.06
    डक
    -0.06
    왼
    -0.06
     disrespect
    -0.06
     bedeutet
    -0.06
     পয়
    -0.06
     delays
    -0.06
    POSITIVE LOGITS
     second
    0.08
    second
    0.08
     Second
    0.07
    Second
    0.07
    第二
    0.07
    DOUBLE
    0.07
     segundo
    0.07
     SECOND
    0.07
    SECOND
    0.07
     второго
    0.06
    Activations Density 0.058%

    No Known Activations