© 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. 119296
    Prev
    Next
    INDEX
    Explanations

    times with am/pm

    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
     casi
    -0.07
     eleven
    -0.07
     nearly
    -0.07
     prawie
    -0.07
     거의
    -0.07
     hampir
    -0.07
     ApJ
    -0.07
    লেখা
    -0.07
     almost
    -0.06
     почти
    -0.06
    POSITIVE LOGITS
    一般
    0.06
     durchschnitt
    0.06
     এমনি
    0.06
    समझ
    0.06
    不做
    0.05
     peculiarity
    0.05
    ತೆಯ
    0.05
     一般
    0.05
     simply
    0.05
     hydrophobic
    0.05
    Activations Density 0.002%

    No Known Activations