© 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. 119476
    Prev
    Next
    INDEX
    Explanations

    location/region assignments

    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
     is
    -0.07
     are
    -0.06
    current
    -0.06
     പ്രത്യേക
    -0.06
     ships
    -0.06
    Aile
    -0.06
     सत्यापन
    -0.06
    wegs
    -0.06
     Special
    -0.06
     rilas
    -0.06
    POSITIVE LOGITS
    roductive
    0.07
    MODULE
    0.06
     among
    0.06
     chosen
    0.06
     childhood
    0.06
    onies
    0.06
    Modules
    0.06
    Mean
    0.05
     subconsciously
    0.05
     inadvertently
    0.05
    Activations Density 0.001%

    No Known Activations