© 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. 120265
    Prev
    Next
    INDEX
    Explanations

    Geographic locations and common words

    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
     ১২শ
    -0.06
     +
    -0.06
     known
    -0.06
    iscal
    -0.06
    LessThan
    -0.06
     standoff
    -0.06
    лес
    -0.06
    mitter
    -0.06
     outages
    -0.05
    copyOf
    -0.05
    POSITIVE LOGITS
     for
    0.09
     this
    0.07
     هذه
    0.07
    ﻫ
    0.07
     these
    0.07
     in
    0.07
     این
    0.07
     эти
    0.06
    這
    0.06
     Association
    0.06
    Activations Density 0.001%

    No Known Activations