© 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. 119717
    Prev
    Next
    INDEX
    Explanations

    at

    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
     obwohl
    -0.07
    ,
    -0.06
     membership
    -0.06
    \},
    -0.06
     இய
    -0.06
     itulah
    -0.06
     Bolts
    -0.05
    resents
    -0.05
    WQ
    -0.05
    ことは
    -0.05
    POSITIVE LOGITS
     this
    0.07
     they
    0.07
     다른
    0.06
    Questo
    0.06
     പൂർ
    0.06
     by
    0.06
     NOW
    0.06
     माफिया
    0.06
     phức
    0.06
     komplex
    0.06
    Activations Density 0.003%

    No Known Activations