© 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. 116312
    Prev
    Next
    INDEX
    Explanations

    GNU General Public License

    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
     the
    -0.06
     umfang
    -0.06
    ning
    -0.05
     B
    -0.05
     (?)
    -0.05
    admin
    -0.05
    ain
    -0.05
    anhyd
    -0.05
    chained
    -0.05
     admin
    -0.05
    POSITIVE LOGITS
    おそらく
    0.07
    または
    0.07
    と思います
    0.07
    もしくは
    0.07
     또는
    0.07
     consequently
    0.07
     Consequently
    0.07
     Wanted
    0.07
    なのか
    0.06
    Whereas
    0.06
    Activations Density 0.001%

    No Known Activations