© 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. 128969
    Prev
    Next
    INDEX
    Explanations

    written by or created by

    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
     these
    -0.09
     they
    -0.09
    こうした
    -0.08
    这些
    -0.08
    これらの
    -0.07
    這些
    -0.07
     这些
    -0.07
     они
    -0.07
    ພວກ
    -0.07
    这些人
    -0.07
    POSITIVE LOGITS
    :
    0.12
     :
    0.06
     এবং
    0.06
     ছাপ
    0.06
    :**
    0.06
    hman
    0.06
     Хотя
    0.06
    ،
    0.06
    ...........
    0.05
     clearest
    0.05
    Activations Density 0.017%

    No Known Activations