© 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. 117061
    Prev
    Next
    INDEX
    Explanations

    about CotEditor

    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
     αριθ
    -0.08
    自分の
    -0.08
    他們
    -0.08
    ពួកគេ
    -0.08
     उनके
    -0.08
     onların
    -0.07
     type
    -0.07
     их
    -0.07
     methods
    -0.07
    얻
    -0.07
    POSITIVE LOGITS
     brings
    0.06
    focused
    0.06
     (@
    0.06
     throughout
    0.06
     pushes
    0.06
     lifted
    0.06
    acting
    0.05
     предстоя
    0.05
     focused
    0.05
    li
    0.05
    Activations Density 0.003%

    No Known Activations