© 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. 117405
    Prev
    Next
    INDEX
    Explanations

    stage classification

    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
     likelihood
    -0.07
    往往
    -0.06
    說
    -0.06
    likelihood
    -0.06
     larges
    -0.06
    という
    -0.06
     ____________
    -0.06
    ということは
    -0.06
     driver
    -0.06
    夠
    -0.05
    POSITIVE LOGITS
     totalement
    0.08
     vollständig
    0.07
     completamente
    0.07
     Estados
    0.07
     only
    0.07
     there
    0.06
     sadece
    0.06
     complètement
    0.06
     entièrement
    0.06
     فقط
    0.06
    Activations Density 0.002%

    No Known Activations