© 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. 129025
    Prev
    Next
    INDEX
    Explanations

    floor plans

    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
     technique
    -0.07
     unquestionably
    -0.06
    dive
    -0.05
     contrasting
    -0.05
     caric
    -0.05
    ยิน
    -0.05
    Details
    -0.05
    pio
    -0.05
    about
    -0.05
    atories
    -0.05
    POSITIVE LOGITS
     может
    0.08
     ένα
    0.08
     یک
    0.07
     शेड्यूल
    0.07
     boleh
    0.07
     根据
    0.07
     puede
    0.07
     může
    0.07
     potrebbe
    0.07
     могла
    0.07
    Activations Density 0.002%

    No Known Activations