© 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. 118493
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
     wäre
    -0.06
     would
    -0.06
    iad
    -0.06
     analys
    -0.06
     related
    -0.06
    aurait
    -0.06
     faintly
    -0.06
     United
    -0.06
     elated
    -0.06
     himself
    -0.05
    POSITIVE LOGITS
     Misalnya
    0.07
     Ethics
    0.07
    procedure
    0.06
    Ethics
    0.06
     menghasilkan
    0.06
     contoh
    0.06
     einzelnen
    0.06
     противопо
    0.06
     gennaio
    0.06
     esimerk
    0.06
    Activations Density 0.006%

    No Known Activations