© 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. 119769
    Prev
    Next
    INDEX
    Explanations

    Q: or Current, Date, or value

    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
     RequestMethod
    -0.07
     메서
    -0.07
    RequestMethod
    -0.07
     misunderstood
    -0.06
     metodo
    -0.06
     sonrisa
    -0.06
     misunderstand
    -0.06
    的方法
    -0.06
     emphasized
    -0.06
     kanilang
    -0.06
    POSITIVE LOGITS
     if
    0.06
     these
    0.06
    cele
    0.06
     బాల
    0.06
     any
    0.06
    快速
    0.05
    Influ
    0.05
     Alignment
    0.05
     made
    0.05
    fast
    0.05
    Activations Density 0.001%

    No Known Activations